FPGA-Based Neural Network Acceleration

Spiking Neural Networks (SNNs) offer a biologically inspired foundation for low-power, event-driven intelligence, yet their direct on-chip supervised training remains a key hardware challenge. This paper presents a multiplication-free, spike-time-based learning algorithm specifically designed for efficient FPGA realization. The proposed approach eliminates floating-point arithmetic and explicit gradient storage, enabling a fully event-driven, digital training pipeline. Implemented on a Xilinx Artix-7 FPGA, the architecture achieves high operating speed and minimal resource usage while maintaining competitive accuracy. These results demonstrate that the learning algorithm effectively maps onto reconfigurable hardware, achieving both computational and energy efficiency. Software simulations further validate scalability, with 96.5% and 84.8% accuracy on MNIST and Fashion-MNIST. With its spike-driven and multiplier-free operation, the proposed framework delivers a practical and scalable hardware solution for real-time, on-chip SNN learning in edge environments.

Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of-the-art LUT-aware training (LAT) approaches remain difficult to use in practice: they are often orders of magnitude slower to train than conventional networks, require non-trivial manual tuning for hardware efficiency, and lack an end-to-end workflow. This work presents HGQ-LUT, integrated in https://github.com/calad0i/HGQ2, a new LAT approach that achieves state-of-the-art hardware efficiency while accelerating training by over 100 times on modern GPUs. HGQ-LUT introduces LUT-Dense and LUT-Conv layers that are implemented with regular, accelerator-efficient tensor operations during training, which are then compiled into logic LUTs for hardware. By combining these layers with fine-grained, element-wise heterogeneous quantization (including zero-bit pruning) and a LUT-aware resource surrogate, HGQ-LUT enables the automatic exploration of accuracy-resource trade-offs without manual bit-width tuning. We further integrate HGQ-LUT into open-source toolchains, enabling unified design, compilation, and bit-exact verification of hybrid architectures that mix LUT-based with conventional arithmetic blocks. These features make LAT-based DNNs practical for real-world deployment, such as at the CERN Large Hadron Collider's experiments.

Complex-Valued Neural Networks (CVNNs) have significant advantages in handling tasks that involve complex numbers. However, existing CVNNs are unable to quantify predictive uncertainty. We propose, for the first time, dropout-based Bayesian Complex-Valued Neural Networks (BayesCVNNs) to enable uncertainty quantification for complex-valued applications, exhibiting broad applicability and efficiency for hardware implementation due to modularity. Furthermore, as the dual-part nature of complex values significantly broadens the design space and enables novel configurations based on layer-mixing and part-mixing, we introduce an automated search approach to effectively identify optimal configurations for both real and imaginary components. To facilitate deployment, we present a framework that generates customized FPGA-based accelerators for BayesCVNNs, leveraging a set of optimized building blocks. Experiments demonstrate the best configuration can be effectively found via the automated search, attaining higher performance with lower hardware costs compared with manually crafted models. The optimized accelerators achieve approximately 4.5x and 13x speedups on different models with less than 10% power consumption compared to GPU implementations, and outperform existing work in both algorithm and hardware aspects. Our code is publicly available at: https://github.com/zehuanzhang/BayesCVNN.git.

Extreme-edge scientific applications use machine learning models to analyze sensor data and make real-time decisions. Their stringent latency and throughput requirements demand small batch sizes and require that model weights remain fully on-chip. Spatial dataflow implementations are common for extreme-edge applications. Spatial dataflow works well for small networks, but it fails to scale to larger models due to inherent resource scaling limitations. AI Engines on modern FPGA SoCs offer a promising alternative with high compute density and additional on-chip memory. However, the architecture, programming model, and performance-scaling behavior of AI Engines differ fundamentally from those of the programmable logic, making direct comparison non-trivial and the benefits of using AI Engines unclear. This work addresses how and when extreme-edge scientific neural networks should be implemented on AI Engines versus programmable logic. We provide systematic architectural characterization and micro-benchmarking and introduce a latency-adjusted resource equivalence (LARE) metric that identifies when AI Engine implementations outperform programmable logic designs. We further propose spatial and API-level dataflow optimizations tailored to low-latency scientific inference. Finally, we demonstrate the successful deployment of end-to-end neural networks on AI Engines that cannot fit on programmable logic when using the hlsml toolchain.

Covert channels (CCs) in wireless chips pose a serious security threat, as they enable the exfiltration of sensitive information from the chip to an external attacker. In this work, we propose an AI-based defense mechanism deployed at the RF receiver, where the model directly monitors raw I/Q samples to detect, in real time, the presence of a CC embedded within an otherwise nominal signal. We first compact a state-of-the-art convolutional neural network (CNN), achieving an 80% reduction in parameters, which is an essential requirement for efficient edge deployment. When evaluated on the open-source hardware Trojan (HT)-based CC dataset, the compacted CNN attains an average accuracy of 90.28% for CC detection and 86.50% for identifying the underlying HT, with results averaged across SNR values above 1 dB. For practical communication scenarios where SNR > 20 dB, the model achieves over 97% accuracy for both tasks. These results correspond to a minimal performance degradation of less than 2% compared to the baseline model. The compacted CNN is further benchmarked against alternative classifiers, demonstrating an excellent accuracy-model size trade-off. Finally, we design a lightweight CNN hardware accelerator and demonstrate it on an FPGA, achieving very low resource utilization and an efficiency of 107 GOPs/W. Being the first AI hardware accelerator proposed specifically for CC detection, we compare it against state-of-the-art AI accelerators for RF signal classification tasks such as modulation recognition, showing superior performance.

Deep neural networks (DNNs) deliver state-of-the-art accuracy on regression and classification tasks, yet two structural deficits persistently obstruct their deployment in safety-critical, resource-constrained settings: (i) opacity of the learned function, which precludes formal verification, and (ii) reliance on heterogeneous, library-bound activation functions that inflate latency and silicon area on edge hardware. The recently introduced Exp-Minus-Log (EML) Sheffer operator, eml(x, y) = exp(x) - ln(y), was shown by Odrzywolek (2026) to be sufficient - together with the constant 1 - to express every standard elementary function as a binary tree of identical nodes. We propose to embed EML primitives inside conventional DNN architectures, yielding a hybrid DNN-EML model in which the trunk learns distributed representations and the head is a depth-bounded, weight-sparse EML tree whose snapped weights collapse to closed-form symbolic sub-expressions. We derive the forward equations, prove computational-cost bounds, analyse inference and training acceleration relative to multilayer perceptrons (MLPs) and physics-informed neural networks (PINNs), and quantify the trade-offs for FPGA/analog deployment. We argue that the DNN-EML pairing closes a literature gap: prior neuro-symbolic and equation-learner approaches (EQL, KAN, AI-Feynman) work with heterogeneous primitive sets and do not exploit a single hardware-realisable Sheffer element. A balanced assessment shows that EML is unlikely to accelerate training, and on commodity CPU/GPU it is also unlikely to accelerate inference; however, on a custom EML cell (FPGA logic block or analog circuit) the asymptotic latency advantage can reach an order of magnitude with simultaneous gain in interpretability and formal-verification tractability.

We present a theoretical analysis and empirical evaluations of a novel set of techniques for computational cost reduction of test time operations of network classifiers based on extreme learning machine (ELM). By exploring some characteristics we derived from these models, we show that the classification at test time can be performed using solely integer operations without compromising the classification accuracy. Our contributions are as follows: (i) We show empirical evidence that the input weights values can be drawn from the ternary set with limited reduction of the classification accuracy. This has the computational advantage of dismissing multiplications; (ii) We prove the classification accuracy of normalized and non-normalized test signals are the same; (iii) We show how to create an integer version of the output weights that results in a limited reduction of the classification accuracy. We tested our techniques on 5 computer vision datasets commonly used in the literature and the results indicate that our techniques can allow the reduction of the computational cost of the operations necessary for the classification at test time in FPGAs. This is important in embedded applications, where power consumption is limited, and crucial in data centers of large corporations, where power consumption is expensive.

Spiking Neural Networks (SNNs) offer a promising solution for energy-efficient edge intelligence; however, their hardware deployment is constrained by memory overhead, inefficient scaling operations, and limited parallelism. This work proposes L-SPINE, a low-precision SIMD-enabled spiking neural compute engine for efficient edge inference. The architecture features a unified multi-precision datapath supporting 2-bit, 4-bit, and 8-bit operations, leveraging a multiplier-less shift-add model for neuron dynamics and synaptic accumulation. Implemented on an AMD VC707 FPGA, the proposed neuron requires only 459 LUTs and 408 FFs, achieving a critical delay of 0.39 ns and 4.2 mW power. At the system level, L-SPINE achieves 46.37K LUTs, 30.4K FFs, 2.38 ms latency, and 0.54 W power. Compared to CPU and GPU platforms, it reduces inference latency from seconds to milliseconds, achieving an up to three orders-of-magnitude improvement in energy efficiency. Quantisation analysis shows that INT2/INT4 configurations significantly reduce memory footprint with minimal accuracy loss. These results establish L-SPINE as a scalable and efficient solution for real-time edge SNN deployment.

Spiking Neural Networks (SNNs) promise significant advantages over conventional Artificial Neural Networks (ANNs) for applications requiring real-time processing of temporally sparse data streams under strict power constraints -- a concept known as the Neuromorphic Advantage. However, the limited availability of neuromorphic hardware creates a substantial simulation-to-hardware gap that impedes algorithmic innovation, hardware-software co-design, and the development of mature open-source ecosystems. To address this challenge, we introduce Yet Another Neuromorphic Accelerator (YANA), an FPGA-based digital SNN accelerator designed to bridge this gap by providing an accessible hardware and software framework for neuromorphic computing. YANA implements a five-stage, event-driven processing pipeline that fully exploits temporal and spatial sparsity while supporting arbitrary SNN topologies through point-to-point neuron connections. The architecture features an input preprocessing scheme that maintains steady event processing at one event per cycle without buffer overflow risks, and implements hardware-efficient event-driven neuron updates using lookup tables for leak calculations. We demonstrate YANA's sparsity exploitation capabilities through experiments on the Spiking Heidelberg Digits dataset, showing near-linear scaling of inference time with both spatial and temporal sparsity levels. Deployed on the accessible AMD Kria KR260 platform, a single YANA core utilizes 740 LUTs, 918 registers, 7 BRAMS and 24 URAMs, supporting up to $2^{17}$ synapses and $2^{10}$ neurons. We release the YANA framework as an open-source project, providing an end-to-end solution for training, optimizing, and deploying SNNs that integrates with existing neuromorphic computing tools through the Neuromorphic Intermediate Representation (NIR).

The demand for high-speed, low-latency, and energy-efficient object detection in autonomous systems -- such as advanced driver-assistance systems (ADAS), unmanned aerial vehicles (UAVs), and Industry 4.0 robotics -- has exposed the limitations of traditional Convolutional Neural Networks (CNNs). To address these challenges, we have developed AceleradorSNN, a third-generation artificial intelligence cognitive system. This architecture integrates a Neuromorphic Processing Unit (NPU) based on Spiking Neural Networks (SNNs) to process asynchronous data from Dynamic Vision Sensors (DVS), alongside a dynamically reconfigurable Cognitive Image Signal Processor (ISP) for RGB cameras. This paper details the hardware-oriented design of both IP cores, the evaluation of surrogate-gradienttrained SNN backbones, and the real-time streaming ISP architecture implemented on Field-Programmable Gate Arrays (FPGA).

Increasing demands for adaptability, privacy, and security at the edge have persistently pushed the frontiers for a new generation of machine learning (ML) algorithms with training and inference capabilities on-chip. Weightless Neural Network (WNN) is such an algorithm that is principled on lookup table based simple neuron structures. As a result, it offers architectural benefits, such as low-latency, low-complexity inference, compared to deep neural networks that depend heavily on multiply-accumulate operations. However, traditional WNNs rely on memorization-based one-shot training, which either leads to overfitting and reduced accuracy or requires tedious post-training adjustments, limiting their effectiveness for efficient on chip training. In this work, we propose TsetlinWiSARD, a training approach for WNNs that leverages Tsetlin Automata (TAs) to enable probabilistic, feedback-driven learning. It overcomes the overfitting of WiSARD's one-shot training with iterative optimization, while maintaining simple, continuous binary feedback for efficient on-chip training. Central to our approach is a field programmable gate array (FPGA)-based training architecture that delivers state-of-the-art accuracy while significantly improving hardware efficiency. Our approach provides over 1000x faster training when compared with the traditional WiSARD implementation of WNNs. Further, we demonstrate 22% reduced resource usage, 93.3% lower latency, and 64.2% lower power consumption compared to FPGA-based training accelerators implementing other ML algorithms.

Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targets leave little slack. TRINE is a single-bitstream FPGA accelerator and compiler that executes end-to-end multimodal inference without reconfiguration. Layers are unified as DDMM/SDDMM/SpMM and mapped to a mode-switchable engine that toggles at runtime among weight/output-stationary systolic, 1xCS SIMD, and a routable adder tree (RADT) on a shared PE array. A width-matched, two-stage top-k unit enables in-stream token pruning, while dependency-aware layer offloading (DALO) overlaps independent kernels across reconfigurable processing units to sustain utilization. Evaluated on Alveo U50 and ZCU104, TRINE reduces latency by up to 22.57x vs. RTX 4090 and 6.86x vs. Jetson Orin Nano at 20-21 W; token pruning alone yields up to 7.8x on ViT-heavy pipelines, and DALO contributes up to 79% throughput improvement. With int8 quantization, accuracy drops remain <2.5% across representative tasks, delivering state-of-the-art latency and energy efficiency for unified vision, language, and graph workloads-in one bitstream.

In this work we present a novel framework for fire safety management in industrial settings through the implementation of a smart camera platform for jet flames characterization. The approach seeks to alleviate the lack of real-time solutions for industrial early fire segmentation and characterization. As a case study, we demonstrate how a SoC FPGA, running optimized Artificial Intelligence (AI) models can be leveraged to implement a full edge processing pipeline for jet flames analysis. In this paper we extend previous work on computer-vision jet fire segmentation by creating a novel experimental set-up and system implementation for addressing this issue, which can be replicated to other fire safety applications. The proposed platform is designed to carry out image processing tasks in real-time and on device, reducing video processing overheads, and thus the overall latency. This is achieved by optimizing a UNet segmentation model to make it amenable for an SoC FPGAs implementation; the optimized model can then be efficiently mapped onto the SoC reconfigurable logic for massively parallel execution. For our experiments, we have chosen the Ultra96 platform, as it also provides the means for implementing full-fledged intelligent systems using the SoC peripherals, as well as other Operating System (OS) capabilities (i.e., multi-threading) for systems management. For optimizing the model we made use of the Vitis (Xilinx) framework, which enabled us to optimize the full precision model from 7.5 million parameters to 59,095 parameters (125x less), which translated into a reduction of the processing latency of 2.9x. Further optimization (multi-threading and batch normalization) led to an improvement of 7.5x in terms of latency, yielding a performance of 30 Frames Per Second (FPS) without sacrificing accuracy in terms of the evaluated metrics (Dice Score).

Spiking Neural Networks (SNNs) offer high energy efficiency and event-driven computation, ideal for low-power edge AI. Their hardware implementation on FPGAs, however, faces challenges due to heavy computation, large memory use, and limited flexibility. This paper proposes a compact System-on-Chip (SoC) architecture for temporal-coding SNNs, integrating a RISC-V controller with an event-driven SNN core. It replaces multipliers with bitwise operations using binarized weights, includes a spike-time sorter for active spikes, and skips noninformative events to reduce computation. The architecture runs fully on a Xilinx Artix-7 FPGA, achieving up to 16x memory reduction for weights and lowering computational overhead and latency, with 97.0% accuracy on MNIST and 88.3% on FashionMNIST. This self-contained design provides an efficient, scalable platform for real-time neuromorphic inference at the edge.

Space missions increasingly deploy high-fidelity sensors that produce data volumes exceeding onboard buffering and downlink capacity. This work evaluates FPGA acceleration of neural networks (NNs) across four space use cases on the AMD ZCU104 board. We use Vitis AI (AMD DPU) and Vitis HLS to implement inference, quantify throughput and energy, and expose toolchain and architectural constraints relevant to deployment. Vitis AI achieves up to 34.16$\times$ higher inference rate than the embedded ARM CPU baseline, while custom HLS designs reach up to 5.4$\times$ speedup and add support for operators (e.g., sigmoids, 3D layers) absent in the DPU. For these implementations, measured MPSoC inference power spans 1.5-6.75 W, reducing energy per inference versus CPU execution in all use cases. These results show that NN FPGA acceleration can enable onboard filtering, compression, and event detection, easing downlink pressure in future missions.

Recurrent Neural Networks (RNNs) are vital for sequential data processing. Long Short-Term Memory Autoencoders (LSTM-AEs) are particularly effective for unsupervised anomaly detection in time-series data. However, inherent sequential dependencies limit parallel computation. While previous work has explored FPGA-based acceleration for LSTM networks, efforts have typically focused on optimizing a single LSTM layer at a time. We introduce a novel FPGA-based accelerator using a dataflow architecture that exploits temporal parallelism for concurrent multi-layer processing of different timesteps within sequences. Experimental evaluations on four representative LSTM-AE models with varying widths and depths, implemented on a Zynq UltraScale+ MPSoC FPGA, demonstrate significant advantages over CPU (Intel Xeon Gold 5218R) and GPU (NVIDIA V100) implementations. Our accelerator achieves latency speedups up to 79.6x vs. CPU and 18.2x vs. GPU, alongside energy-per-timestep reductions of up to 1722x vs. CPU and 59.3x vs. GPU. These results, including superior network depth scalability, highlight our approach's potential for high-performance, real-time, power-efficient LSTM-AE-based anomaly detection on FPGAs.

Gated DeltaNet (GDN) is a linear attention mechanism that replaces the growing KV cache with a fixed-size recurrent state. Hybrid LLMs like Qwen3-Next use 75% GDN layers and achieve competitive accuracy to attention-only models. However, at batch-1, GDN decode is memory-bound on GPUs since the full recurrent state must be round-tripped through HBM every token. We show that this bottleneck is architectural, not algorithmic, as all subquadratic sequence models exhibit arithmetic intensities below 1 FLOP/B at decode time, making them more memory-bound than standard Transformers. We present an FPGA accelerator that eliminates this bottleneck by holding the full 2 MB recurrent state persistently in on-chip BRAM, converting the workload from memory-bound to compute-bound. Our design fuses the GDN recurrence into a five-phase pipelined datapath that performs only one read and one write pass over each state matrix per token, exploits Grouped Value Attention for paired-head parallelism, and overlaps preparation, computation, and output storage via dataflow pipelining. We explore four design points on an AMD Alveo U55C using Vitis HLS, varying head-level parallelism from 2 to 16 value-heads per iteration. Our fastest configuration achieves 63 $μ$s per token, 4.5$\times$ faster than the GPU reference on NVIDIA H100 PCIe. Post-implementation power analysis reports 9.96 W on-chip, yielding up to 60$\times$ greater energy efficiency per token decoded.

Accurate sea ice mapping is essential for safe maritime navigation in polar regions, where rapidly changing ice conditions require timely and reliable information. While Sentinel-1 Synthetic Aperture Radar (SAR) provides high-resolution, all-weather observations of sea ice, conventional ground-based processing is limited by downlink bandwidth, latency, and energy costs associated with transmitting large volumes of raw data. On-board processing, enabled by dedicated inference chips integrated directly within the satellite payload, offers a transformative alternative by generating actionable sea ice products in orbit. In this context, we present TinyIceNet, a compact semantic segmentation network co-designed for on-board Stage of Development (SOD) mapping from dual-polarized Sentinel-1 SAR imagery under strict hardware and power constraints. Trained on the AI4Arctic dataset, TinyIceNet combines SAR-aware architectural simplifications with low-precision quantization to balance accuracy and efficiency. The model is synthesized using High-Level Synthesis and deployed on a Xilinx Zynq UltraScale+ FPGA platform, demonstrating near-real-time inference with significantly reduced energy consumption. Experimental results show that TinyIceNet achieves 75.216% F1 score on SOD segmentation while reducing energy consumption by 2x compared to full-precision GPU baselines, underscoring the potential of chip-level hardware-algorithm co-design for future spaceborne and edge AI systems.

Real-time unmanned aerial vehicle (UAV) acoustic detection at the edge demands low-latency inference under strict power and hardware limits. This paper presents SHIELD8-UAV, a sequential 8-bit hardware implementation of a precision-aware 1D feature-driven CNN (1D-F-CNN) accelerator for continuous acoustic monitoring. The design performs layer-wise execution on a shared multi-precision datapath, eliminating the need for replicated processing elements. A layer-sensitivity quantisation framework supports FP32, BF16, INT8, and FXP8 modes, while structured channel pruning reduces the flattened feature dimension from 35,072 to 8,704 (75%), thereby lowering serialised dense-layer cycles. The model achieves 89.91% detection accuracy in FP32 with less than 2.5% degradation in 8-bit modes. The accelerator uses 2,268 LUTs and 0.94 W power with 116 ms end-to-end latency, achieving 37.8% and 49.6% latency reduction compared with QuantMAC and LPRE, respectively, on a Pynq-Z2 FPGA, and 5-9% lower logic usage than parallel designs. ASIC synthesis in UMC 40 nm technology shows a maximum operating frequency of 1.56 GHz, 3.29 mm2 core area, and 1.65 W total power. These results demonstrate that sequential execution combined with precision-aware quantisation and serialisation-aware pruning enables practical low-energy edge inference without relying on massive parallelism.

Lightweight neural network accelerators are essential for edge devices with limited resources and power constraints. While quantization and binarization can efficiently reduce hardware cost, they still rely on the conventional Artificial Neural Network (ANN) computation pattern. The recently proposed Kolmogorov-Arnold Network (KAN) presents a novel network paradigm built on learnable nonlinear functions. However, it is computationally expensive for hardware deployment. Inspired by KAN, we propose BiKA, a multiply-free architecture that replaces nonlinear functions with binary, learnable thresholds, introducing an extremely lightweight computational pattern that requires only comparators and accumulators. Our FPGA prototype on Ultra96-V2 shows that BiKA reduces hardware resource usage by 27.73% and 51.54% compared with binarized and quantized neural network systolic array accelerators, while maintaining competitive accuracy. BiKA provides a promising direction for hardware-friendly neural network design on edge devices.

Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization technologies in related lightweight accelerator designs to reduce hardware resource consumption. However, low precision leads to high accuracy loss in inference. Therefore, mixed-precision quantization becomes an alternative solution by applying different precision in different layers to trade off resource consumption and accuracy. Because regular designs for multiplication on hardware cannot support the precision reconfiguration for a multi-precision Quantized Neural Network (QNN) model in runtime, we propose a runtime reconfigurable multi-precision multi-channel bitwise systolic array design for QNN accelerators. We have implemented and evaluated our work on the Ultra96 FPGA platform. Results show that our work can achieve 1.3185 to 3.5671 times speedup in inferring mixed-precision models and has less critical path delay, supporting a higher clock frequency (250MHz).

Deep learning (DL) has emerged as a rapidly developing advanced technology, enabling the performance of complex tasks involving image recognition, natural language processing, and autonomous decision-making with high levels of accuracy. However, as these technologies evolve and strive to meet the growing demands of real-life applications, the complexity of DL models continues to increase. These models require processing of massive volumes of data, demanding substantial computational power and memory bandwidth. This gives rise to the critical need for hardware accelerators that can deliver both high performance and energy efficiency. Accelerator types include ASIC based solutions, GPU accelerators, and FPGA based implementations. The limitations of ASIC and GPU accelerators have led to FPGAs becoming one of the prominent solutions, offering distinct advantages for DL workloads. FPGAs provide a flexible and reconfigurable platform, allowing model specific customization while maintaining high efficiency. This article explores various hardware level optimizations for DL. These optimizations include techniques such as loop pipelining, parallelism, quantization, and various memory hierarchy enhancements. In addition, it provides an overview of state-of-the-art FPGA-based neural network accelerators. Through the study and analysis of these accelerators, several challenges have been identified, paving the way for future optimizations and innovations in the design of FPGA-based hardware accelerators.

This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach leverages a sensitivity-based pruning mechanism to identify and remove less critical quantized weights with minimal impact on model accuracy, thereby reducing computational overhead while preserving accuracy. We perform an extensive trade-off analysis to validate the effectiveness of the proposed framework and the impact of pruning and quantization on model performance and hardware parameters. For this evaluation, we employ three time-series datasets, including both classification and regression tasks. Experimental results across selected benchmarks demonstrate that our proposed approach maintains high accuracy while substantially improving computational and resource efficiency in FPGA-based implementations, with variations observed across different configurations and time series applications. For instance, for the MELBOEN dataset, an accelerator quantized to 4-bit at a 15% pruning rate reduces resource utilization by 1.2% and the Power Delay Product (PDP) by 50.8% compared to an unpruned model, without any noticeable degradation in accuracy.

This brief presents a runtime-adaptive, performance-enhanced vector engine featuring a low-resource, iterative CORDIC-based MAC unit for edge AI acceleration. The proposed design enables dynamic reconfiguration between approximate and accurate modes, exploiting the latency-accuracy trade-off for a wide range of workloads. Its resource-efficient approach further enables up to 4x throughput improvement within the same hardware resources by leveraging vectorised, time-multiplexed execution and flexible precision scaling. With a time-multiplexed multi-AF block and a lightweight pooling and normalisation unit, the proposed vector engine supports flexible precision (4/8/16-bit) and high MAC density. The ASIC implementation results show that each MAC stage can save up to 33% of time and 21% of power, with a 256-PE configuration that achieves higher compute density (4.83 TOPS/mm2 ) and energy efficiency (11.67 TOPS/W) than previous state-of-the-art work. A detailed hardware-software co-design methodology for object detection and classification tasks on Pynq-Z2 is discussed to assess the proposed architecture, demonstrating a scalable, energy-efficient solution for edge AI applications.

As the volume of data recorded by embedded edge sensors increases, particularly from neuromorphic devices producing discrete event streams, there is a growing need for hardware-aware neural architectures that enable efficient, low-latency, and energy-conscious local processing. We present an FPGA implementation of event-graph neural networks for audio processing. We utilise an artificial cochlea that converts time-series signals into sparse event data, reducing memory and computation costs. Our architecture was implemented on a SoC FPGA and evaluated on two open-source datasets. For classification task, our baseline floating-point model achieves 92.7% accuracy on SHD dataset - only 2.4% below the state of the art - while requiring over 10x and 67x fewer parameters. On SSC, our models achieve 66.9-71.0% accuracy. Compared to FPGA-based spiking neural networks, our quantised model reaches 92.3% accuracy, outperforming them by up to 19.3% while reducing resource usage and latency. For SSC, we report the first hardware-accelerated evaluation. We further demonstrate the first end-to-end FPGA implementation of event-audio keyword spotting, combining graph convolutional layers with recurrent sequence modelling. The system achieves up to 95% word-end detection accuracy, with only 10.53 microsecond latency and 1.18 W power consumption, establishing a strong benchmark for energy-efficient event-driven KWS.

Dataflow-based CNN accelerators on FPGAs achieve low latency and high throughput by mapping computations of each layer directly to corresponding hardware units. However, layers such as pooling and strided convolutions reduce the data at their output with respect to their input, strongly effecting the data rate of the following layers. This leads to underutilization in fully unrolled designs. While prior work introduced data-rate-aware layer-wise adaptation, determining the most efficient implementation remains challenging. This paper presents a data-rate-aware CNN accelerator architecture for multi-pixel processing. Building on existing analytical models, the proposed method performs design-space exploration to identify configurations that improve hardware utilization and resource efficiency while preserving continuous flow of data, keeping all hardware units busy. Experimental results show substantial reductions in arithmetic resources compared to previous designs, enabling efficient implementation of complex CNNs on a single FPGA across a wide range of data rates.

This paper presents an end-to-end demonstration of a viable, ultra-fast, radiation-hard machine learning (ML) application on FPGAs, which could be used in future high-energy physics experiments. We present a three-fold contribution, with the PicoCal calorimeter, planned for the LHCb Upgrade II experiment, used as a test case. First, we develop a lightweight autoencoder to compress a 32-sample timing readout, representative of that of the PicoCal, into a two-dimensional latent space. Second, we introduce a systematic, hardware-aware quantization strategy and show that the model can be reduced to 10-bit weights with minimal performance loss. Third, as a barrier to the adoption of on-detector ML is the lack of support for radiation-hard FPGAs in the High-Energy Physics community's standard ML synthesis tool, hls4ml, we develop a new backend for this library. This new back-end enables the automatic translation of ML models into High-Level Synthesis (HLS) projects for the Microchip PolarFire family of FPGAs, one of the few commercially available and radiation hard FPGAs. We present the synthesis of the autoencoder on a target PolarFire FPGA, which indicates that a latency of 25 ns can be achieved. We show that the resources utilized are low enough that the model can be placed within the inherently protected logic of the FPGA. Our extension to hls4ml is a significant contribution, paving the way for broader adoption of ML on FPGAs in high-radiation environments.

Gradient-based LUT- and logic-gate-based neural networks (LUTNet, LogicNets, DiffLogic, PolyLUT, NeuraLUT, WARP-LUT, DWN, LILogicNet, LightLUT) replace multiply-accumulate arithmetic with Boolean lookups. The same trained checkpoint deploys to GPU as bitwise ops on bit-packed activations, to FPGA as LUT primitives, and to ASIC as standard-cell gates, all from one code path. Yet each method ships its own training pipeline, encoder, connectivity rule, fan-in, and hardware-reporting convention. The natural practitioner question, which of these choices actually matter for accuracy and which for hardware cost, therefore has no answer in the current literature. We release BitLogic, a unified framework that factors the field into a five-axis design space (encoder, connectivity, fan-in, node parameterization, head) and instantiates every prior method under one shared training and evaluation protocol. The framework deliberately omits method-specific procedures such as calibration, pruning, and thresholding, and all evaluations are limited to two-layer feed-forward networks. Combining the per-axis winners identifies a new best-of-space configuration that outperforms every retrained prior on every (dataset, width) cell in which every compared prior fits the shared budget, across MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. We evaluate the best-of-space model on all three backends. On MNIST, the resulting two-layer network reaches ${\sim}126$,MSamples/s on FPGA, ${\sim}15\times$ the throughput of a bit-packed GPU forward path that itself processes $64$ samples per $64$-bit operation, at four-to-five orders of magnitude less energy.

Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops required to densely convolve every input pixel regardless of its feature value. However, input features can be spatially sparse in some image data, where semantic information may occupy only a small fraction of the pixels and most computation would be wasted on empty regions. In this work, we introduce SparsePixels, a framework that implements sparse convolution on FPGAs by selectively retaining and computing on a small subset of active input pixels while ignoring the rest, reducing the per-layer compute from $O(HWK^2C_{\text{in}}C_{\text{out}})$ to $O(n^2C_{\text{in}}C_{\text{out}})$ and the storage from $O(HWC)$ to $O(nC)$ when $n^2\ll HW$. Because computation always runs over a single pre-specified pixel budget that is frozen at synthesis, the inference latency is data-independent and constant at runtime. We show that, for identifying neutrino interactions in naturally sparse LArTPC images with 4k pixels, a standard CNN with a compact size of 4k parameters incurs an inference latency of 48.665 $μ$s on an FPGA, whereas a sparse CNN of the same base architecture, computing on less than 1% of the input pixels, achieves a $\times 73$ speedup to 0.665 $μ$s with resource utilization well within on-chip budgets, trading only a small percent-level performance loss. This work aims to benefit future algorithm development for efficient data readout in modern experiments with strict latency requirements of microseconds or below.

This paper examines the use of Quantized Neural Networks (QNNs) for two resource-constrained scientific applications: automated calibration of semiconductor quantum bits (qubits) and scientific particle detectors. We evaluate the trade-offs between Post-Training Quantization (PTQ), Quantization-Aware Training (QAT), and ultra-low-bit Binary Neural Networks (BNNs) with respect to latency and resource usage. Our results demonstrate that PTQ and QAT are easily implementable solutions achieving a four-fold reduction in memory usage for Ushaped CNN (U-Net) architectures, whereas BNNs are better suitable for use cases with challenging latency requirements. For the training of non-differentiable custom BNNs, we propose a novel, hardware-constrained learning approach using Genetic Algorithms (GAs). We showcase a Look-Up Table (LUT)-based BNN architecture suitable for direct conversion to Very High-Speed Integrated Circuit Hardware Description Language (VHDL) via the HCL4BNN framework. This method achieves nanosecond-scale inference latencies at 10 ns to 15 ns without requiring specialized Digital Signal Processor (DSP) or Block RAM (BRAM) resources.