Predictive coding studies how systems can infer, learn, or compress information by predicting incoming data and correcting mismatches. In neuroscience, hierarchical Bayesian and free-energy models use precision-weighted prediction errors to explain perception and action; in machine learning, predictive coding networks use local updates, while equilibrium propagation, feedback pathways, and amortized inference aim to make training faster and deeper. Related predictive methods forecast future inputs or code residuals for tasks such as video, language, and data compression, with evaluations spanning CIFAR and ImageNet, time-series benchmarks, and alignment to visual-cortex responses. A central tension is whether local, biologically inspired computation can match backpropagation and scale to deep or long-range tasks without giving up efficiency or hardware simplicity.
Predictive coding (PC) trains neural networks through local energy-minimization dynamics without depending on a global error signal that backpropagation (BP) requires. Although PC is a promising alternative algorithm for efficient learning, the computational cost of inference dynamics currently outweighs the resulting learning benefits in practice. In this work, we take inspiration from optimization theory to extract more learning benefit from each inference phase. We introduce Natural PC, which augments standard PC with a lateral circuit, enabling exact and efficient natural gradient learning locally in space and time. Our lateral circuit learns the activity correlations that determine the Fisher information matrix and implicitly computes its inverse, avoiding expensive matrix inversion. Across all tested image reconstruction benchmarks, Natural PC achieves state of the art in terms of sample and compute efficiency compared to existing PC approaches. Most notably, Natural PC scales to ImageNet and matches the performance of BP trained with AdamW and various second-order optimizers at an order of magnitude lower computational cost while also using two orders of magnitude fewer training samples. Our results demonstrate that local natural gradient learning makes PC competitive with BP in both sample efficiency and computational cost in reconstruction tasks.
Lhea Beumer, Sander de Haan, Niclas Pokel +2
Institute of Neuroinformatics, UZH & ETH Zurich · ETH AI Center
Animals integrate information across sensory modalities to guide exploration, suggesting that they maintain internal estimates of where actions are expected to reduce uncertainty. However, how such action-conditioned information maps are learned from multimodal sensory experience remains unclear, as previous studies have been largely confined to unimodal sensing frameworks. We introduce a multimodal predictive-coding framework for learning uncertainty-reduction maps from visual and mechanosensory observations in hawkmoth flower interaction tasks. A variational generative model trained on simulated environments recovers modality-specific information landscapes over the action space, capturing how visual patterns, surface geometry, and mechanosensory cues shape the value of exploratory actions. These learned maps are consistent with several features of hawkmoth behavior, including nonzero tracking offsets, probing along visual patterns, and geometry-dependent exploration. Applying the model to behavioral data from flower tracking and nectary search, we find that natural trajectories tend to occupy regions of high uncertainty reduction in these learned maps. Building on these observations, we develop an uncertainty-gated lexicographic algorithm that switches between information gathering and reward exploitation based on perceptual uncertainty. In nectary search, uncertainty gating improves learning relative to exploit-only, ε-greedy, fixed-time, and uncertainty-calibrated non-lexicographic controls, with better generalization and robustness to sensory and curvature shifts. These results link information landscapes learned through generative modeling to biological sensing and embodied exploration.
Abdelrahman Sharafeldin, Yaqing Wang, Simon Sponberg +1
Machine Learning Center, Georgia Institute of Technology, Atlanta, GA 30332 · School of Physics, Georgia Institute of Technology, Atlanta, GA 30332 · School of Mathematics, Georgia Institute of Technology, Atlanta, GA 30332
Perceptual audio codecs often use predictive coding to further reduce signal redundancy. Rather than learning the entire codec pipeline end-to-end, we insert a small neural network as a drop-in, deterministic predictor in an otherwise conventional codec: the network estimates the next Modified Discrete Cosine Transform (MDCT) coefficient block from a short context of reconstructed blocks, and the encoder transmits the quantized residual. We compare Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) predictors against a non-predictive baseline and a per-line Normalized Least Mean Squares (NLMS) linear predictor (similar to the MPEG-2 AAC Main Profile predictor). The CNN consistently outperforms the MLP, the linear predictor, and the baseline in signal-to-noise ratio (SNR), noise-to-mask ratio (NMR), and MUSHRA evaluation scores. Using a 512-sample analysis window (w = 512), our neural predictors recover, and the CNN exceeds, the coded quality obtained by the non-predictive baseline after quadrupling the analysis-window length to w = 2048, at substantially lower algorithmic delay. The CNN uses only 0.13M parameters (roughly 20x fewer than the MLP) and has a decoder real-time factor (RTF) of ~0.10 on a consumer CPU.
Niccolo Abate, Gabriel Soule, Marina Bosi
Center for Computer Research in Music and Acoustics (CCRMA), Stanford University, Stanford, CA, USA
The transition of information-centric artificial intelligence to safety-critical applications is impeded by the limitations of conventional offline-training paradigms in open-world environments. This paper presents Control AI, an architecture for Online Active Learning (OAL) inspired by the continuous Prediction-Evaluation-Correction process of biological intelligence. The framework combines the hierarchical representation capacity of deep neural networks with the real-time error-feedback adaptation of adaptive control. A prediction model maps sensory input into a latent manifold, an optional latent model represents transitions in that space, and a reconstruction model maps the latent state back to observable signals. Residuals between predictions and measurements provide the internal learning signal. Spatial and temporal cross-reconstruction architectures prevent OAL from collapsing to a trivial identity mapping, while coupled, dual, and localized variants shorten error-transmission paths. Localized predictive coding style OAL is implemented through guidance-backpropagation and target-backpropagation architectures, and hybrid and scaled variants support high-dimensional deployment. The paper focuses on the architectural rationale and the progression from a conceptual feedback loop to practical large-scale configurations.
Shuiwen Shen, Jinhua Zhang, Yan Wang +5
School of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen, 361024, China. · State Innovative Centre for Automotive Electric Driving at Xiamen, Xiamen, Fujian, 361010, China. · China Innovation Center for Intelligent and Connected Vehicles, Beijing, 100176, China. +2
Dynamic systems evolve continuously over time, whereas observations in real scenarios are often sparse, irregular, and asynchronous. Accurate prediction therefore requires inferring latent state evolution between observations, as future values depend on partially observed trajectories. We propose Predictive Coding Dynamics (PCD), a residual feedback mechanism for irregular continuous dynamic models. PCD maintains previous reconstructions, predicts observed entries from them, and incorporates masked signed residuals into state recognition through an energy penalty. The mechanism is implemented with ODE-RNN and Latent ODE, supporting event-based hidden updates and latent state recognition. Experiments on forecasting and trajectory recovery tasks show that PCD improves continuous dynamic backbones under sparse and irregular sampling. The results further indicate that predictive error feedback improves latent state estimation when observations constrain the current trajectory. These results suggest that PCD provides a residual feedback framework that jointly supports trajectory generation, observation consistency checking, and state refinement in continuous-time series modeling. The source code is available at https://anonymous.4open.science/r/PCD-for-paper-92F1/.
Tianrui Gou, Jiayangmei Xu, Xingzhou Zhang +1
School of Artificial Intelligence, Beihang University, Beijing 100191, China. · Department of Foreign Languages, Beihang University, Beijing 100191, China.
In continuous spiking keyword spotting, temporally correlated acoustic frames can repeatedly trigger memory access and neural computation at a dense input interface, even when hidden activity is sparse. Predictive processing and sensory adaptation suggest retaining predictable input locally and responding selectively to deviations. Inspired by this mechanism, we propose Predictive Gating Signed-Dyadic Coding (PG). PG maintains a local prediction for each input channel and transmits an event only when the residual exceeds a learned threshold. Each event carries a sign and a finite power-of-two magnitude, and the receiver reconstructs it with fixed-point shifts and additions. In Mandarin keyword spotting, INPUT-PG reaches 90.00% accuracy while reducing mean SRAM reads by 33.87% and inference cycles by 32.77%. PG provides a hardware interface for research on low-power continuous speech processing and event-based sensory systems.
Zijian Zhou, Rui Liu, Rongxiang Nie +3
Sivy Limited, Hangzhou, China · The Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge, UK
Temporal Predictive Coding (tPC) networks offer a layer-local alternative to backpropagation. For linear tPC, we show, by applying tools from cellular sheaf theory, that temporal credit assignment is a tug-of-war between spatial displacement and temporal errors, whose ratios are modulated by persistence and exposure operators P and Q. Spatial inference therefore gives us the effective recurrent transition F=PA, whilst future credit is filtered by P∗. This creates a persistence--error tradeoff in spatial modes: under non-amplifying invariant recurrence, modes that preserve influence over long delays simultaneously fail to expose that influence strongly as temporal error. Recurrence can circumvent this via routing between persistent and exposed modes.
On a chain of N states, any local learning rule with bounded communication range needs Θ(N) rounds before the loss can influence the earliest parameters, and this latency is usually attributed to depth. We show that it is a property of the communication geometry rather than of depth. For N=md states placed at constant density in d dimensions, a light-cone argument gives an Ω(N1/d) lower bound on the number of bounded-range rounds that any local algorithm needs before its gradient estimates can be sign-correct at every parameter. We construct a unit-range, degree-2d directed acyclic graph that contains a Hamiltonian computation of length N−1 and in which every state lies within directed distance d(m−1)=Θ(N1/d) of the output, matching the lower bound. In the realizable-circuit model, depth and credit depth are therefore independent parameters: represented depth Θ(N) and causal credit latency Θ(N1/d) coexist, with a separation of order N1−1/d. SpatialPC realizes this separation within predictive coding. Credit is propagated by adjoint prediction dynamics (APD), a local update whose K-round state on a settled acyclic graph is the truncated reverse-path sum aK=∑k<K(J⊤)kb, with error exactly (J⊤)Ka⋆. Graph geometry fixes when credit can first arrive at a state; the Jacobian-weighted path tail fixes how many further rounds accurate credit requires. A sparse two-dimensional Moore compiler retains the N−1 backbone with 23N−2 unit-range edges and has measured worst-node reachability N+2 up to N=65,536, where a 65,535-edge backbone is reached in 258 local hops. With T=2N rounds, SpatialPC keeps finite-round task gradients aligned with settled gradients (cosine 0.93 on MNIST and 0.97 on Fashion-MNIST at N=256) and reaches 97.6% and 88.1% test accuracy after 20 epochs.
Benjamin Prada, Shion Matsumoto, Ankur Arjun Mali
Trustworthy Knowledge-Driven AI Lab Bellini College of Artificial Intelligence, Cybersecurity and Computing University of South Florida Tampa, FL 33620
Traditional neural video compression (NVC) methods predominantly follow strictly causal predictive-coding paradigm, treating zero-frame delay as a fixed constraint rather than delay as an explicit design parameter. From an information-theoretic perspective, allowing limited frame delay enables a codec to exploit correlations with future frames within the delay window, thereby reducing uncertainty that is inaccessible to strictly causal prediction and potentially improving the rate-distortion tradeoff. In this work, we formalize this intuition through a rigorous rate-distortion analysis builds on the clique factorization of Markov networks, and propose Graph-Factored Sequential Coding (GFSC), a principled framework for sequential video coding under limited delay. To our knowledge, we provide the first theoretical result showing that, for general K-order Markov sources with positive distributions, a K-frame delay is sufficient to attain joint-coding rate-distortion optimality over a nontrivial distortion region, a guarantee unavailable to zero-delay causal coding in general. In practice, we instantiate GFSC through lightweight neural modules, allowing existing causal predictive codecs to be augmented without modifying their core architectures. Experiments across multiple NVC models and datasets show that GFSC consistently improves rate-distortion performance over the corresponding causal counterparts. Under matched delay budgets, GFSC also achieves competitive performance compared with representative bidirectional codecs.
Long-running agents retain KV caches across turns and sessions for hours or days. Compressing these persistent caches requires reducing storage while controlling reconstruction error. We present AlignPred, a codec that combines local alignment with predictive coding under a configurable KV reconstruction-error budget. Local orthogonal transforms align related heads or layers into a common coordinate frame, allowing AlignPred to combine token-wise prediction with same-token prediction across heads or layers. Residuals are quantized on an error-bounded lattice and entropy-coded, without learned predictors, encoder-side mode search, or large joint transforms. Across three attention mechanisms, AlignPred requires less storage than the evaluated baselines at comparable measured reconstruction error. Against the evaluated CPU codec implementations, it decodes at least 1.6 times faster while matching or improving encode time. AlignPred achieves near-native task scores at substantially compressed operating points on LongBench-Pro at 128K context. AlignPred's SGLang HiCache integration reduces persistent target-KV storage by 42-72% relative to native HiCache, with comparable latency.
Xu Yang, Jiapeng Zhang, Zhiwei Zuo +5
Hunan University · Central China Normal University · Tencent
Predictive coding networks (PCNs) promise properties not offered by backpropagation-trained networks: learning from purely local information, a single network that both discriminates and generates, and flexible inference by energy minimization. However, their iterative inference is expensive, making hardware acceleration desirable, and a useful, efficient accelerator needs both depth and aggressive quantization. Canonical state-based PC delivers neither: its inference signal decays exponentially with depth, so deep models fail to train, and low precision makes it worse. We show that pairing two recent methods carries the full PCN property set into the deep, 4-bit regime: bidirectional PC (bPC), which unifies discrimination and generation, and the error-based reparameterization (ePC), which optimizes prediction errors rather than states during inference. Error optimization delivers the output signal to every layer in a single backward pass, removing the signal decay; one additional element, global-norm clipping of the error gradients, stabilizes the error dynamics at depth. The resulting ePC+bPC model trains stably up to at least eight layers and retains its full-precision accuracy and clean class-conditional generation under W4A4E4 quantization-aware training, across FP4 and three posit formats. On six-layer networks, where state-based bPC collapses to chance, ePC+bPC classifies more than 50 accuracy points above it after one epoch of training, with class-conditional generations 5-9x better in RMSE. 4-bit quantization is nearly free: full-precision and 4-bit accuracies differ by at most ~5 points, and by under two in the best-performing formats. We characterize the two failure modes the method overcomes, bounded signal decay in state-based PC and error divergence in unregularized error optimization, and discuss implications for a 4-bit-native PCN accelerator.
Garrett Kinman, Zeljko Zilic
Department of Electrical and Computer Engineering, McGill University, Montréal, Québec, Canada
Test-time memorization of sequential information is a foundational capability for any intelligent system that needs to rapidly store and retrieve data, as demonstrated by the attention mechanism in large language models. However, Transformers and linear attention variants are trained via backpropagation through time (BPTT), which has drawbacks such as its enormous memory requirements. Predictive coding (PC), an algorithm that optimizes a prediction-error energy function with local updates, offers a compelling solution but still lacks test-time memory for sequential data. We develop a solution to this problem by treating the per-step memory update ΔSt as a latent variable, as opposed to a slow weight to be learned. By taking the log probability of a standard PC-based probabilistic model, we derive a PC-native solution for verbatim sequence memory, and relate our update rule to common choices in the linear attention literature (e.g., DeltaNet). We present an extensive set of empirical tests to probe our system's properties, including its scaling capacity, memory footprint, and ability to infer a context from evidence (e.g., bank (river) vs. bank (money)). We show how DeltaNet-PC can be used for storing single sequences of data, multiple sequences of data, and key-value associative memory pairs with perfect recall accuracy.
Todd Morrill, Richard Zemel
Computer Science, Columbia University New York, NY, USA
Generating an image with a diffusion or flow-matching model typically involves integrating a velocity field for hundreds of sequential steps. That computation suits a GPU poorly and an analog neuromorphic substrate well, where one fast, low-power physical relaxation could replace the whole sequence. Two things are needed: a generative algorithm whose computation is a relaxation, and a way to train it without backpropagation, whose global gradient transport is hard to realise in analog. Energy Matching supplies the first, sampling by gradient-descent relaxation on a time-independent potential - but obtaining the gradient that descent follows is itself a backward pass, once per integration step. We prove that a predictive coding network with a single linear injection term added to its energy relaxes to a state whose visible layer carries that gradient inherently, with an error that vanishes for small injection strengths. An Energy Matching model trained by backpropagation can therefore be loaded into this network unchanged and sampled by relaxation alone, matching the original model's FID to within 0.04 at CIFAR-10 and ImageNet-32 scale. The network can also be trained without backpropagation: Equilibrium Propagation reproduces backpropagation's parameter updates to a cosine similarity of 0.9998, and training end to end with those updates reaches an FID of 3.64 on unconditional CIFAR-10 against 3.54 for backpropagation. To our knowledge this is the first CIFAR-10 generative model trained with Equilibrium Propagation, and the first at competitive quality by any backpropagation-free rule. This quality does not require group normalisation or attention: an architecture of only convolutions and pointwise nonlinearities, both native to an analog crossbar, reaches an FID of 3.51 when trained by backpropagation.
Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimuli has enabled us to better understand human visual processing. However, studies so far have largely overlooked the fact that the human brain not only processes observed visual stimuli, but also predicts upcoming stimuli based on what has been observed. Accordingly, we hypothesize that internal representations for generating future video frames are better aligned with the predictive nature of human visual processing than representations of the observed video itself. To this end, we compare the alignment between human video-watching fMRI responses in the visual cortex and the internal representations from two types of video diffusion models, an autoregressive (AR) model and its non-AR base model. We first conduct a within-model analysis of the AR video diffusion model and show that the representations for future video generation align better with the visual cortex than the representations of the observed video. We then compare the internal representations of the AR model with those of its non-AR base model and again show that the representations for future video generation align better with the visual cortex than the representations for observed video reconstruction by the base model. Specifically, the alignment of observed video reconstruction is concentrated in lower-order visual cortex, whereas that of future video generation is concentrated in higher-order visual cortex. Finally, we show in a human behavioral experiment that humans prefer videos generated by amplifying the contributions of individual layers that align better with the visual cortex.
Chang-Bae Bang, Hyungjin Chung, Byung-Hoon Kim
Department of Psychiatry, Yonsei University College of Medicine · Institute of Behavioral Sciences in Medicine, Yonsei University College of Medicine · Department of Biomedical Systems Informatics, Yonsei University College of Medicine +2
Predictive coding (PC) is a local, energy-based alternative to backpropagation (BP) whose iterative inference dynamics make it attractive for implementation on analog hardware. However, standard nonlinear PC requires evaluating the derivative of the activation function during both inference and learning, which can be difficult to realise physically. Here, we introduce activation-matched Bregman PC, replacing standard squared-error energies with Bregman divergences matched to the activation function. This formulation eliminates activation derivatives and, when combined with inference via mirror descent, yields local inference and learning rules requiring only weighted sums, local prediction errors, state integration, and the activation function. In digital experiments, Bregman PC performs comparably to standard PC and BP on classification and generative tasks, while preserving characteristic learning dynamics of PC and its convergence to BP under stable large-model parameterisations. These results provide a more analog-friendly formulation of nonlinear PC while retaining its key computational properties.
Francesco Innocenti
Brain Network Dynamics Unit University of Oxford, UK
Feedforward Spiking Neural Networks (SNNs) typically propagate every generated spike indiscriminately, disregarding whether the information is redundant from an information-theoretic perspective. This lack of selectivity induces high redundancy in inter-layer communication, creating an expensive overhead, e.g., in scenarios involving many-core neuromorphic hardware or communication-dominated Internet-of-Things (IoT) where features are transmitted wirelessly. To address this challenge, we trade localized processing for leaner network channels by introducing a minimal predictive coding framework for SNNs. We propose two layer variants sharing a predictor block: error units, which transmit signed spiking residuals, and predictive suppression, which uses residual magnitude to dynamically gate and forward only unpredictable, "surprising" activity. Evaluated on the N-MNIST and Spiking Heidelberg Digits (SHD) datasets using diagnostic metrics that decouple local processing from cross-layer communication, our new predictive coding layers achieve significant communication savings. Numerical results reveal a three-fold reduction in communicated activity, while increasing the task accuracy for both datasets. The latter finding is notable, and suggests that predictive coding layers not only minimize communication overhead, but also produce output feature vectors with a higher representation power.
Aidin Attar, Michele Rossi
University of Padova Department of Information Engineering Padova, Italy · University of Padova Dept. of Inf. Eng. and Dept. of Mathematics Padova, Italy
Predictive coding characterizes adaptive behavior as a dynamic balance between internally generated predictions and external sensory evidence, yet how an embodied cognitive system can regulate this balance online during ongoing interaction remains poorly understood. This study proposes a predictive-coding-based mechanism for regulating internally generated and externally coupled processing during physical human--robot interaction. The framework employs a predictive-coding-inspired variational recurrent neural network (PV-RNN), in which a meta-prior controls the degree to which posterior inference is constrained by learned prior dynamics. We extend this architecture with an online mechanism that uses reconstruction error accumulated over recent interaction history to select between predefined meta-prior regimes. The mechanism was evaluated across three physical human--robot interaction tasks involving fixed structured, changing structured, and less-constrained interaction. Across all tasks, lower meta-prior values produced the expected increase in posterior--prior divergence and reduction in reconstruction error. More importantly, reconstruction-history-driven regime selection was also associated with reduced prospective prediction error and robot-side physical interaction conflict, demonstrating consequences beyond the retrospective reconstruction objective itself. Task~3 further showed that recent sensory observations can be successfully accommodated while subsequent human motion still departs from the model's prior-generated future trajectory. Overall, these findings show that accumulated reconstruction mismatch can provide an endogenous signal for regulating how strongly subsequent inference relies on learned internal dynamics relative to ongoing sensory input during embodied interaction.
Henrique Oyama, Hiroki Sawada, Jun Tani
Cognitive Neurorobotics Research Unit Okinawa Institute of Science and Technology Graduate University Okinawa
We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series foundation model (Google TimesFM-3) with an adaptive arithmetic coder, guaranteeing ∣x^t−xt∣≤τ on every sample. One negative result constrains the design space: for lossless coding a foundation model is worth nothing, because bits saved are logarithmic in predictor accuracy, Δb=log2(MAEold/MAEnew). So the 1.51× advantage TimesFM-3 holds over a 32-tap linear predictor buys 0.60 bits of 20.28, a median gain of +0.03%. Error-bounded coding escapes this at one point: once a forecast lands inside the band the residual index is zero and the sample nearly free. Cadence contributes: (1) an adaptive range coder with context-modelled binarization, beating xz/zstd on real indices by 9.7% (15/15) and reversing a finding from a general-purpose back end; (2) a determinism result -- predictions are not bit-identical across batch sizes, and no PyTorch configuration repairs this, forcing group size and execution device into the container format; and (3) domain localization on corpora postdating any plausible training cutoff. On 49 EIA-930 balancing-authority demand series (2026) Cadence gains 13.3% over the best of six classical predictors, and 28.3% on 50 MTA ridership series (2026): 21.4% median over 297 series-tolerance pairs, winning all 297. Against downsampling, what time-series databases deploy for retention, its guaranteed worst-case error is 28--56× tighter at equal size. End-to-end, once the context bootstrap is paid for, gains run from 6.8% at six months of hourly data to 15.1% asymptotically. Attempting to falsify the domain claim on SDRBench, theory predicts failure and delivers: -0.8% median, 0 of 27 pairs gaining. Three further negative results and eight retracted claims are reported in full.
Local learning methods offer an alternative to end-to-end backpropagation, but their unstructured local objectives can produce weak feature learning in deep networks. We study whether the order of hidden-state optimization can address this limitation. We propose a boundary-first inference schedule that partitions a model into chunks, first coordinates hidden states at chunk boundaries, and then refines representations within each chunk. We instantiate this schedule in predictive coding networks (PCNs), a local-learning framework in which hidden activities and prediction errors are explicitly exposed during inference. On CIFAR-10, the resulting boundary-first predictive-coding instantiation improves accuracy over standard predictive coding by 9.77% under a standard parametrization and by 5.51% under a μ-parametrization. Diagnostic analyses further show more non-trivial early-layer updates, lower initial-to-final CKA, and more diverse layerwise gradients, consistent with stronger feature learning. These results support boundary-first, chunk-based inference as a practical design principle for predictive-coding training and motivate its study in broader local-learning systems.
Predictive Coding (PC) is a neural learning paradigm that enables parallelizable neural network layer updates. However, the main bottleneck of PC Networks (PCN) is the sequential backwards error propagation. To tackle this, we introduce a training technique that pairs a Generative PCN with a support Encoding PCN. The two PCNs are trained in parallel to match their neural activations, without sequential propagation. We apply this to time series anomaly detection and show that our approach results in more stable, continuous, online learning.
Matteo Cardoni, Sam Leroux
IDLab, Department of Information and Technology, Ghent University—imec, 9052 Ghent, Belgium
Fully online embodied learning requires synaptic adaptation to acquire new behaviors while preserving previously learned dynamics during ongoing interaction. We extend the Predictive-Coding-inspired Variational Recurrent Neural Network (PV-RNN) to continuously adapt its synaptic weights and propose Free-Energy-Gated Plasticity (FEGP), which regulates the effective learning rate according to variational free energy. In real-time physical human-robot interaction, a randomly initialized network acquired three cyclic motor patterns without offline pretraining, replay, or task-boundary signals, with all three patterns emerging in autonomous rollouts. Controlled experiments over ten randomized teaching streams and five network initializations per stream showed that FEGP substantially improved repertoire coverage and retention of previously acquired patterns after they left the recent observation window. Neither a constant learning rate matched to the gate's time-averaged effective rate nor replay of the same gain values with disrupted temporal organization reproduced these improvements. These results indicate that the temporal allocation of plasticity relative to model-environment mismatch, rather than simply its average magnitude or distribution, is critical for maintaining previously acquired behaviors during continued online learning.
Hiroki Sawada, Jun Tani
Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan 904-0302
We propose IM-LEPP (Integrated Multimodal Latent Energy-based Predictive Processing), a hierarchical, energy-based model of multimodal cognition that extends a previously proposed single-modality model (LEPP) to integrate vision and language. Following the view that generative neural networks are effective theories of cognitive dynamics, analogous to how statistical mechanics relates to thermodynamics, IM-LEPP models cognition as latent states flowing through learned energy landscapes rather than as an account of neural circuitry. The architecture is a hub-and-spoke hierarchy, grounded in the controlled semantic cognition framework of Lambon Ralph et al., in which predictive-coding pipelines for visual objects, scenes, and linguistic units converge on a shared amodal hub modeled on the anterior temporal lobe. Each pipeline's own prediction is conditioned by, rather than overwritten by, the current hub state, preserving pipeline-specific identity while letting every prediction reflect the full multimodal context. We show this architecture gives a mechanistic account of attentional phenomena such as inattentional blindness and Necker-cube bistability, and that its structure recovers or motivates independently established findings in psycholinguistics, including surprisal theory, the N400/P600 ERP components, and garden-path reanalysis, alongside a falsifiable contrast with transformer language models on trajectory-sensitivity in next-word prediction. We also discuss data-efficient language acquisition relative to LLMs, outline a semantic/episodic memory subsystem, situate the model against predictive coding, the free-energy principle, JEPA, and Hierarchical Temporal Memory, and propose concrete experimental predictions to test its central claims Key Words: predictive processing; predictive coding; energy-based models; diffusion models; effective theory; computational neuroscience.
We study the topology of learned representations in predictive coding networks (PCNs), a neuro-inspired bidirectional architecture, using a quantitative layer-wise persistent homology analysis. We train well-performing PCNs on a synthetic classification dataset (≥99.9% test accuracy) and on MNIST (≥95% test accuracy), and measure how topological features change across layers for different architectures and activation functions. We find that smaller PCNs collapse connected components across layers earlier than larger models (Spearman \unicodex1D70C∈[0.72,0.79] across activations), with model size measured as the sum of hidden-layer widths. We also observe a strong negative correlation (\unicodex1D70C=−0.58) between the depth at which simplification occurs and reconstruction error; i.e., architectures that simplify later reconstruct better. Finally, a seed-level bootstrap comparison across architectures and activations shows that PCNs consistently collapse connected components later than matched MLPs, with an average difference of 3.6 layers. These results suggest that persistent homology offers a useful quantitative lens on the compression--reconstruction tradeoff in PCNs, and that both model capacity and the recurrent, bidirectional dynamics of predictive coding inference shape when this tradeoff is resolved across layers.
Adam Shaw, Jiayu Li, Michael Sperling +2
University of Southern California 3551 Trousdale Parkway, Los Angeles, CA 90089
Predictive processing theories portray the brain as a hierarchical prediction engine that minimizes prediction error, yet they lack operational definitions for the structure of a "prediction," the standardized response to a prediction error, and the mechanism that maintains consistency across successive updates. Bayesian cognitive science attempts to subsume all uncertainty under probabilistic belief updating, but it presupposes a closed hypothesis space and provides no generative account of how the objects over which probabilities are distributed become discrete, identifiable referents in the first place. This paper introduces Predictive Set Theory (PST), a formal generative framework that reconstructs cognitive architecture from first principles. PST anchors cognition in a minimal set of operations---a sensor formalized as an identity function, set-theoretic state refresh, and three fundamental forms of reference chains (reference, counter-reference, and semi-reference)---and rigorously derives core cognitive functions including state sequences, demand, comparison, efficiency, and finite-horizon probabilistic planning. Rather than modeling neural mechanisms, PST constitutes a design specification for any system that must maintain internal consistency while acting under incomplete information and irreversible risk. The framework offers novel resolutions to classical problems such as Russell's paradox, the cognitive status of Gödelian incompleteness, the grounding of negative feedback, and the comprehension of film editing. The primary purpose of this paper is to establish, through the public academic record, the originality and completeness of the Predictive Set Theory framework.
Predictive coding offers a powerful framework for cortical computation, yet scalable implementations that respect both Bayesian exactness and neurobiological constraints remain scarce. We bridge this gap by formally connecting predictive coding to Recursive Gaussian Processes (RGPs). RGPs employ a single Gaussian process g(t,⋅) indexed by layer index and input value, preventing the representational collapse of standard deep Gaussian processes while allowing learnable cross-layer dependence via r1g. We demonstrate that RGPs intrinsically implement hierarchical Bayesian inference, uncertainty propagation, and precision-weighted prediction error. Critically, we map RGP components---the shared GP, spike-and-slab variable selection, and MCMC dynamics---onto the canonical cortical microcircuit, providing a neurobiological substrate for these computations. Drawing on the free energy principle, we show that RGP inference minimizes variational free energy, formally linking Bayesian mechanics to neuronal dynamics. Our synthesis positions RGPs as both a principled computational tool and a candidate model for the brain's predictive machinery, generating testable predictions for laminar-specific dynamics and spectral asymmetries between feedforward and feedback processing.
Moumita Das, Dipanjan Ray, Sourabh Bhattacharya
1Indian Institute of Management, Udaipur, India · Department of Psychology and Cognitive Sciences, Ashoka University, Haryana, India · 3Koita Centre for Digital Health at Ashoka (KCDH-A), Haryana, India +1
Predictive coding offers a powerful theory of cortical computation, but corresponding scalable algorithmic implementations for artificial intelligence have remained elusive. This paper introduces the Bayesian reflex, a computational framework that directly instantiates predictive coding through three pillars: belief maintenance via hierarchical generative models, sequential Bayesian updating via prediction-error minimization, and uncertainty-driven action via active inference. We show that recent breakthroughs---ellipsoidal decomposition for exact i.i.d. sampling, recursive Gaussian processes for deep hierarchical inference, and derivative-aware Bayesian optimization---provide the missing algorithmic ingredients. The resulting framework enables mathematically principled, scalable, and brain-inspired continual learning, perception, and decision-making. We illustrate its versatility through applications ranging from climate model evaluation to prime number discovery, offering a blueprint for truly adaptive artificial intelligence.
Sourabh Bhattacharya
Interdisciplinary Statistical Research Unit Indian Statistical Institute, Kolkata
In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches enable decentralized agents to learn messages grounded in their own observations, but they rely only on current observations and cannot convey information accumulated over time. We propose Dreamer-CPC, a decentralized model-based MARL method that integrates message learning based on Collective Predictive Coding (CPC) into the world model of DreamerV3. Each agent independently maintains a world model and a message module, and infers and exchanges messages from the latent states of the world model that reflect the history of past observations and actions. We evaluated Dreamer-CPC in two environments: Observer, a non-cooperative information-sharing task, and CatchApple, a newly introduced task in which task-relevant observations are temporarily missing. In both environments, Dreamer-CPC outperformed IPPO-CPC, an existing CPC-based method that generates messages from current observations, as well as no-communication baselines. In particular, in CatchApple, Dreamer-CPC achieved 4 to 5 times the episode return of IPPO-CPC, demonstrating effective coordination where other methods fail due to missing observations. These results suggest that communication grounded in the latent dynamics of world models can support decentralized decision-making when current observations alone are insufficient.
In this paper we propose DCVC-Mamba (DCVC-MB), a neural video codec framework for B-frame coding. Our approach incorporates an IBP frame strategy for low-delay B-frame coding, a spatio-temporal fusion model based on state-space models for bidirectional temporal prediction, and an entropy-aware skipping mechanism that selectively omits coding certain latents to reduce entropy coding times. In addition to our model contributions we also implement two inference-time strategies that enhance compression performance. Experimental evaluation shows that DCVC-MB compares favorably to existing NVCs and traditional codecs. The method demonstrates BD-rate reductions of up to 8.98% on average compared to prior neural video codecs, and improvements of up to 30.45% and 1.81% over the VTM-19.0-LDP and VTM-19.0-RA(Inter-GoP=16) benchmarks, respectively, contributing to advances in neural video compression.
Arjun Arora, Calvin-Khang Ta, Carlos Restrepo-Galeano +7
Dolby Laboratories · Voia · University of Delaware +1
Predictive Coding (PC) offers a biologically motivated alternative to backpropagation via local weight updates, yet routing error between layers still relies on an autograd Jacobian-transpose (J⊤) product - the last non-local operation in PC. We show that this dependency is largely avoidable. For any layer f(x)=Act(Norm(L(x))) with frozen normalization statistics, the exact J⊤ factors into three locally available terms, J⊤v=L⊤(s⊙σ′(z)⊙v), where σ′ is the activation derivative, z is the pre-activation, and s=γ/σrun is the normalization gain. Prior weight-feedback methods omitted both corrections; restoring them closes the transport gap for this layer class. Locality here holds up to three assumptions, which we state upfront: weight symmetry (L⊤ mirrors the forward operator, as assumed by all PC), a soft spectral-norm control that is not synapse-local, and a nearest-neighbour approximation for MaxPool. Substituting the identity into PC yields WF-Act-PC, which removes the autograd backward pass from error transport. On CIFAR-10/100 (50 epochs, 5 seeds), WF-Act-PC is the only PC method whose accuracy improves with depth, surpassing iPC - the strongest classical PC baseline - by 2.7-22.3 pp on CIFAR-10. With both methods tuned per architecture, it matches or exceeds a comparably-tuned backpropagation baseline on the deeper CIFAR-10 architectures (VGG-9: 93.57% vs. 92.43%; ResNet-18: 92.76% vs. 91.54%) and on the harder Tiny-ImageNet benchmark, while trailing tuned BP on the deeper CIFAR-100 VGG cells. Our WF-Act-PC implementation is publicly available at https://github.com/jlshen025/pcax
Junlong Shen, Xingyu Li
Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada · Alberta Machine Intelligence Institute (Amii), Edmonton, Canada
Hierarchical predictive coding provides an interpretable framework for perception as error-driven inference in multi-layer generative models, while sparse coding imposes parsimonious latent representations through explicit sparsity constraints. Their combination yields hierarchical sparse predictive coding models with appealing computational and neuroscientific properties, but practical use is often limited by the cost of iterative latent inference. In such models, each input may require many recurrent refinement steps before a useful sparse representation is obtained, and this burden becomes more severe as the hierarchy deepens. We study this bottleneck by holding the hierarchical sparse energy fixed and varying the inference procedure. The comparison includes four schemes: classical iterative inference based on ISTA, an accelerated MFISTA reference, structurally informed amortized inference using a LISTA-style bottom-up encoder adapted to the hierarchical model, and a hybrid method in which this fast amortized initialization is followed by a small number of corrective energy-based refinement steps. Under this shared objective, we measure reconstruction quality, sparsity, latency, and stability on static image benchmarks. The results show that a shallow LISTA-style initializer plus short corrective recurrence improves over pure amortization while remaining much faster than long iterative inference.
Kazuhisa Fujita
Department of Clinical Engineering, Komatsu University, 10-10 Doihara-Machi, Komatsu, Ishikawa, Japan 923-0921