Neural Network Interpretability

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 450% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 203

All topics

A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution
Jul 10, 2026Jose Luis Lima de Jesus SilvaNeural Algorithmic Reasoning Neural Network Interpretability
Federal University of Bahia, Department of Geophysics, Salvador, BA 40170-115, Brazil · Grupo de Estudos e Aplicação de Inteligência Artificial em Geofísica (GAIA), Federal University of Bahia, Salvador, BA 40170-115, Brazil
All you need is SAMPAT
Jul 10, 2026Jayadeva, Madhur AswaniShallow Neural Networks Interpretable ML
Department of Electrical Engineering, Indian Institute of Technology, Delhi
How are linear representations learned? Exact solutions to the dynamics of abstraction
Jul 9, 2026William W. Yang, Andrew M. Saxe, Peter E. LathamLinear Representation Hypothesis Deep Linear Networks
Gatsby Computational Neuroscience Unit, University College London, London W1T 4JG, United Kingdom. · Sainsbury Wellcome Centre, University College London, London W1T 4JG, United Kingdom.
Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence
Jul 9, 2026Yann Claes, Pierre Geurts, Vân Anh Huynh-ThuInterpretable ML Neural Network Interpretability
Montefiore Institute University of Liège
Structural Bottlenecks on Frequency Representation in End-to-End Audio Models
Jul 9, 2026Nicole Cosme-CliffordAudio Representation Learning Neural Audio Codecs
Yale University New Haven, CT
Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation
Jul 8, 2026Ahsan Habib Akash, Dipkamal Bhusal, Stacey Jones +3Concept-Based Explanations Neural Network Interpretability
West Virginia University, USA · Rochester Institute of Technology, USA · O Analytics +3
Unraveling Machine Behavior by Multi-Level Bias Analysis and Detection: Methodology and Application to Computer Vision
Jul 8, 2026Ignacio Serna, Aythami Morales, Julian FierrezNeural Network Interpretability Algorithmic Bias
Center for Humans and Machines, Max Planck Institute for Human Development, Berlin, Germany · BiometricsAI, UAM, Madrid, Spain · Department of Mathematics, ULPGC, Spain
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
Jul 8, 2026Tobias Göbel, Julian R. Ebelt, Zier Mensch +2Phase Transitions Neural Network Interpretability
Institute of Physics, University of Amsterdam, Amsterdam, Netherlands · Department of Physics, National Taiwan University, Taipei, Taiwan · Department of Physics, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA +2
On the Principles of Deep Feedforward ReLU Networks
Jul 8, 2026Changcun HuangReLU Neural Networks Neural Network Interpretability
Shuitu Institute of Applied Mathematics, Chongqing 400700, P.R.C
X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
Jul 7, 2026Jie Huang, Pengfei Yin, Zihan Xu +3Neural Surrogate Modeling Neural Network Interpretability
School of Computing and Information Systems, University of Melbourne, Melbourne, Australia · Department of General Medicine, Royal Melbourne Hospital Melbourne, Australia
Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders
Jul 5, 2026Sohaib AfifiGradient-Based Attribution Counterfactual Explanations
Univ. Artois, UR 3926, Laboratoire de G´enie Informatique et d’Automatique de l’Artois (LGI2A), F-62400 B´ethune, France
Individual Parameters in Weight-Sparse Transformers Appear Interpretable
Jul 3, 2026Arnau Marin-Llobet, Stefan HeimersheimTransformer Interpretability Transformer
School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138
Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data
Jul 2, 2026Mojgan Alishiri, Amirhossein ArzaniNeural Network Interpretability Operator Learning
1Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT, 84112, United States · 2Mechanical Engineering Department, University of Utah, Salt Lake City, UT, 84112, United States
Geometry-Aware R-Structured Kolmogorov-Arnold Networks
Jul 1, 2026Sergei Kucherenko, Nilay ShahNeural Network Interpretability Kolmogorov-Arnold Networks
Imperial College London, London SW7 2AZ, UK
Neuro-Bayesian-Symbolic Residual Attention Shallow Network: Explainable Deep Learning for Cybersecurity Risk Assessment
Jun 29, 2026Nicolaie Popescu-Bodorin, Madeleine TogherShallow Neural Networks Explainable Artificial Intelligence
Engineering & Computer Science Department Spiru Haret University, Bucharest, Romania · Computer Information Science Department Higher Colleges Technologies, Sharjah, U.A.E.
Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization
Jun 29, 2026Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton +1Interpretable ML Neural Network Interpretability
1Oslo Metropolitan University (OsloMet) · 2Simula Metropolitan Center for Digital Engineering (SimulaMet)
Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders
Jun 25, 2026Nathanaël Jacquier, Maria Vakalopoulou, Mahdi S. HosseiniActivation Sparsity Sparse Autoencoders
Université Paris-Saclay, CentraleSupélec, France · Department of Computer Science and Software Engineering (CSSE), Concordia University, Montreal, QC, Canada · Université Paris-Saclay, CentraleSupélec, Gustave Roussy, INSERM, IHU PRISM, Cancer Data Science Unit, France +2
Expresso-AI: Explainable Video-Based Deep Learning Models for Depression Diagnosis
Jun 24, 2026Felipe Moreno, Sharifa Alghowinem, Hae Won Park +1Depression Detection Neural Network Interpretability
Media Lab MIT Cambridge, USA
Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
Jun 23, 2026Thomas Fel, Matthew Kowal, Mozes Jacobs +22Neural Representation Geometry Activation Sparsity
•Goodfire · aHarvard University · bStanford University +1
Interpretable Kolmogorov-Arnold Network with Feature-Isolated Temporal Attention Mechanism for Electricity Load Forecasting
Jun 22, 2026Jinhao Li, Hao WangMultivariate Time Series Forecasting Time Series Forecasting
Department of Data Science and AI, Faculty of Information Technology, Monash University, Melbourne, Victoria, Australia · Monash Energy Institute, Monash University, Melbourne, Victoria, Australia
Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation
Jun 22, 2026Yanze Xu, Mark D. Plumbley, Wenwu WangGradient-Based Attribution Feature Attribution
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, UK · Department of Informatics, King’s College London, London, WC2R 2LS, UK
From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks
Jun 20, 2026Sepideh Kheirollahi, Mohammad Rasoul RoshanshahElectroencephalography EEG Seizure Detection
School of Electrical and Computer Engineering College of Engineering, University of Tehran Tehran, Iran
What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study
Jun 20, 2026Yaozhong Kang, Jiang Wang, Runwu Shi +3Direction-of-Arrival Estimation Neural Network Interpretability
Department of Systems and Control Engineering, Institute of Science Tokyo, Japan
What Do Lorentz-Equivariant Jet Taggers Learn?
Jun 19, 2026Jay Agarwal, Siddharth Khare, Dhruv KumarJet Tagging Equivariant Neural Networks
BITS Pilani, Pilani, India.
Targeted Recovery of Weight-Space Mechanisms From Neural Networks
Jun 19, 2026Antoine Vigouroux, Lee SharkeyTransformer Interpretability Circuit Discovery
1MATS · 2Goodfire
LISE : Listenable Interpretable Speaker Embeddings
Jun 19, 2026Xiaoliang Wu, Chongxin Gan, Ke Liu +2Audio Representation Learning Speaker Verification
University of Southampton, United Kingdom · The Hong Kong Polytechnic University, Hong Kong SAR, China · University of Edinburgh, United Kingdom
A Neurosymbolic Framework for Interpretable Skeleton-Based Seizure Detection via Concept-Driven Logical Reasoning
Jun 19, 2026Talha Ilyas, Deval Mehta, Zongyuan GeConcept-Based Explanations Neural Network Interpretability
Department of ECSE, Faculty of Engineering, Monash University, Australia · AIM for Health Lab, Faculty of IT, Monash University, Australia · Department of DSAI, Faculty of IT, Monash University, Australia +1
Critical Percolation as a Synthetic Data Model for Interpretability
Jun 18, 2026Aryeh Brill, Tom Ingebretsen CarlsonSynthetic Data Generation Neural Network Interpretability
Principles of Intelligence
Neural Additive and Basis Models with Feature Selection and Interactions
Jun 18, 2026Yasutoshi Kishimoto, Kota Yamanishi, Takuya Matsuda +1Feature Interaction Modeling Neural Network Interpretability
Yokohama National University, Kanagawa, Japan
Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
Jun 18, 2026Haocheng Duan, Yuxin Guo, Jieyi Bi +4Neural Network Interpretability Neural Combinatorial Optimization
1Carnegie Mellon University · 2Nanyang Technological University · 3Microsoft Research +1

Jul 10, 2026, cs.AIJ/K move · Enter open · S save

A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution

Jose Luis Lima de Jesus Silva

Federal University of Bahia, Department of Geophysics, Salvador, BA 40170-115, Brazil · Grupo de Estudos e Aplicação de Inteligência Artificial em Geofísica (GAIA), Federal University of Bahia, Salvador, BA 40170-115, Brazil

Neural Algorithmic Reasoning Neural Network Interpretability Neuro-Symbolic Reasoning Algorithmic Reasoning

Open paper AskPDF arXiv

Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden. To make those transitions visible, we introduce a trace-supervised symbolic neural CPU, a factorized learned execution architecture that combines recurrent control, an explicit operation router over a fixed differentiable arithmetic-logic unit bank, destination-masked register writeback, complete trajectory supervision and matched fixed-point replay. The model exposes the selected operation, source and destination registers, register trajectory, memory signals and writeback semantics at every step. On the principal 16-wide benchmark, the non-quantized executor reproduces reference execution exactly, while the eight-bit quantization-simulated executor preserves the symbolic operation path through programs of 1,000 instructions. When the same execution is evaluated against a matched fixed-point replay, the residual numerical drift disappears, showing that it comes from a mismatch between continuous and low-precision reference semantics rather than from execution failure. We compare recurrent, Transformer, temporal-convolution, temporal graph-inspired and state-space controllers, and the ablations show that operation-gate supervision is necessary for an inspectable execution path. Hidden-opcode memory-pressure tasks expose the remaining limits in delayed state use and temporal binding. We also extend the interface with ValueMemory, hybrid adaptive leaky integrate-and-fire controllers, candidate-constrained symbolic control trained through behaviour cloning and actor-critic reinforcement learning, and an RV32I base-integer semantic bridge. Together, these results establish a trace-verifiable framework for interpretable, low-precision and controllable neural execution.

Momentum

Related topics

Latest papers 203