{"total":141,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100,"area":null},{"id":"2107.12979","title":"Predictive Coding: a Theoretical and Experimental Review","created":"2021-07-27","cited_by_count":77,"area":null},{"id":"2111.05177","title":"On Training Implicit Models","created":"2021-11-09","cited_by_count":75,"area":null},{"id":"2101.10832","title":"Revisiting Locally Supervised Learning: an Alternative to End-to-end Training","created":"2021-01-26","cited_by_count":71,"area":null},{"id":"2210.03310","title":"Scaling Forward Gradient With Local Losses","created":"2022-10-07","cited_by_count":65,"area":null},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2209.00530","title":"Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations","created":"2022-09-01","cited_by_count":42,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2301.01452","title":"The Predictive Forward-Forward Algorithm","created":"2023-01-04","cited_by_count":35,"area":null},{"id":"2308.07870","title":"Brain-inspired Computational Intelligence via Predictive Coding","created":"2023-08-15","cited_by_count":30,"area":null},{"id":"2106.07887","title":"Credit Assignment in Neural Networks through Deep Feedback Control","created":"2021-06-15","cited_by_count":29,"area":null},{"id":"2206.02629","title":"Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning","created":"2022-05-31","cited_by_count":26,"area":null},{"id":"2305.15947","title":"Online learning of long-range dependencies","created":"2023-05-25","cited_by_count":25,"area":null},{"id":"2204.01723","title":"Signal Propagation: A Framework for Learning and Inference In a Forward Pass","created":"2022-04-04","cited_by_count":24,"area":null},{"id":"2103.04689","title":"Reverse Differentiation via Predictive Coding","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2302.01647","title":"Blockwise Self-Supervised Learning at Scale","created":"2023-02-03","cited_by_count":22,"area":null},{"id":"2106.01288","title":"Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence","created":"2021-06-02","cited_by_count":21,"area":null},{"id":"2106.07030","title":"The Backpropagation Algorithm Implemented on Spiking Neuromorphic Hardware","created":"2021-06-13","cited_by_count":19,"area":null},{"id":"2206.11769","title":"Single-phase deep learning in cortico-cortical networks","created":"2022-06-23","cited_by_count":19,"area":null},{"id":"2206.00164","title":"A Theoretical Framework for Inference Learning","created":"2022-06-01","cited_by_count":17,"area":null},{"id":"2207.01332","title":"The least-control principle for local learning at equilibrium","created":"2022-07-04","cited_by_count":16,"area":null},{"id":"2211.03481","title":"Predictive Coding beyond Gaussian Distributions","created":"2022-11-07","cited_by_count":16,"area":null},{"id":"2106.06199","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2103.03725","title":"Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks","created":"2021-03-05","cited_by_count":14,"area":null},{"id":"2302.01228","title":"Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons","created":"2023-02-02","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2212.04129","title":"Deep Incubation: Training Large Models by Divide-and-Conquering","created":"2022-12-08","cited_by_count":13,"area":null},{"id":"2302.05440","title":"Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2107.07046","title":"Backprop-Free Reinforcement Learning with Active Neural Generative Coding","created":"2021-07-10","cited_by_count":12,"area":null},{"id":"2102.01955","title":"Predictive coding feedback results in perceived illusory contours in a recurrent neural network","created":"2021-02-03","cited_by_count":10,"area":null},{"id":"2104.04657","title":"Meta-Learning Bidirectional Update Rules","created":"2021-04-10","cited_by_count":10,"area":null},{"id":"2204.07249","title":"Minimizing Control for Credit Assignment with Strong Feedback","created":"2022-04-14","cited_by_count":10,"area":null},{"id":"2211.12047","title":"Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images","created":"2022-11-22","cited_by_count":10,"area":null},{"id":"2407.05623","title":"Momentum Auxiliary Network for Supervised Local Learning","created":"2024-07-08","cited_by_count":10,"area":null},{"id":"2108.13446","title":"Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms","created":"2021-08-30","cited_by_count":9,"area":null},{"id":"2212.04614","title":"Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backprop","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2309.02214","title":"Improving equilibrium propagation without weight symmetry through Jacobian homeostasis","created":"2023-09-05","cited_by_count":9,"area":null},{"id":"2402.17318","title":"Scaling Supervised Local Learning with Augmented Auxiliary Networks","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2212.10249","title":"Learning efficient backprojections across cortical hierarchies in real time","created":"2022-12-20","cited_by_count":8,"area":null},{"id":"2306.02149","title":"A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions","created":"2023-06-03","cited_by_count":8,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2503.24322","title":"NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2407.04117","title":"Predictive Coding Networks and Inference Learning: Tutorial and Survey","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2103.05636","title":"A Gradient Estimator for Time-Varying Electrical Networks with Non-Linear Dissipation","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2109.15089","title":"Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks","created":"2021-09-30","cited_by_count":6,"area":null},{"id":"2209.09174","title":"Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2212.10352","title":"Fixed-Weight Difference Target Propagation","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2305.14974","title":"Block-local learning with probabilistic latent representations","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2403.18929","title":"A Review of Neuroscience-Inspired Machine Learning","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2405.08967","title":"Gradient-Free Training of Recurrent Neural Networks using Random Perturbations","created":"2024-05-14","cited_by_count":6,"area":null},{"id":"2406.00446","title":"Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2101.03419","title":"Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods","created":"2021-01-09","cited_by_count":5,"area":null},{"id":"2105.07231","title":"Bilevel Programs Meet Deep Learning: A Unifying View on Inference Learning Methods","created":"2021-05-15","cited_by_count":5,"area":null},{"id":"2406.16633","title":"MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2407.05638","title":"HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2409.19841","title":"Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2110.11501","title":"Cortico-cerebellar networks as decoupling neural interfaces","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2301.07635","title":"Local Learning with Neuron Groups","created":"2023-01-18","cited_by_count":4,"area":null},{"id":"2411.02001","title":"Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2501.09238","title":"Mono-Forward: Revisiting Forward-Forward through Objective-Locality Decomposition","created":"2025-01-16","cited_by_count":4,"area":null},{"id":"2112.01453","title":"Target Propagation via Regularized Inversion","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2112.09214","title":"Sparse Coding with Multi-Layer Decoders using Variance Regularization","created":"2021-12-16","cited_by_count":3,"area":null},{"id":"2302.10802","title":"A Novel Noise Injection-based Training Scheme for Better Model Robustness","created":"2023-02-17","cited_by_count":3,"area":null},{"id":"2304.13372","title":"Feed-Forward Optimization With Delayed Feedback for Neural Network Training","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2407.12516","title":"Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2412.02482","title":"What should a neuron aim for? Designing local objective functions based on information theory","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2112.03615","title":"Saliency Diversified Deep Ensemble for Robustness to Adversaries","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2201.11782","title":"An Empirical Analysis of Recurrent Learning Algorithms In Neural Lossy Image Compression Systems","created":"2022-01-27","cited_by_count":2,"area":null},{"id":"2206.01820","title":"A Robust Backpropagation-Free Framework for Images","created":"2022-06-03","cited_by_count":2,"area":null},{"id":"2308.12053","title":"Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2310.20599","title":"Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignment","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2402.08573","title":"Two Tales of Single-Phase Contrastive Hebbian Learning","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2410.19055","title":"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2501.16476","title":"Closed-Form Feedback-Free Learning with Forward Projection","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2511.18567","title":"In Search of Goodness: Large Scale Benchmarking of Goodness Functions for the Forward-Forward Algorithm","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2605.24797","title":"HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithm","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2102.11598","title":"Gradient-adjusted Incremental Target Propagation Provides Effective Credit Assignment in Deep Neural Networks","created":"2021-02-23","cited_by_count":1,"area":null},{"id":"2203.05417","title":"Deep Regression Ensembles","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2303.16067","title":"Lazy learning: a biologically-inspired plasticity rule for fast and energy efficient synaptic plasticity","created":"2023-03-26","cited_by_count":1,"area":null},{"id":"2306.01870","title":"Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2309.17348","title":"Intrinsic Biologically Plausible Adversarial Robustness","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2403.11004","title":"Forward Learning of Graph Neural Networks","created":"2024-03-16","cited_by_count":1,"area":null},{"id":"2409.12038","title":"A Unified Framework for Neural Computation and Learning Over Time","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2410.01239","title":"Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2503.02642","title":"Spike-based alignment learning solves the weight transport problem","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2505.05181","title":"Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2506.05878","title":"A projection-based framework for gradient-free and parallel learning","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2510.03273","title":"Learning without Global Backpropagation via Synergistic Information Distillation","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2602.00062","title":"SCPL: Enhancing Neural Network Training Throughput with Decoupled Local Losses and Model Parallelism","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2603.03234","title":"Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representations","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2605.31022","title":"Augmented Lagrangian Predictive Coding","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.18574","title":"Conditioned Direct Feedback Alignment via Activity and Error Geometry","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2106.05569","title":"Front Contribution instead of Back Propagation","created":"2021-06-10","cited_by_count":0,"area":null},{"id":"2109.11863","title":"Learning Multi-Layered GBDT Via Back Propagation","created":"2021-09-24","cited_by_count":0,"area":null},{"id":"2110.10379","title":"Cascaded Compressed Sensing Networks: A Reversible Architecture for Layerwise Learning","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2110.15305","title":"Cooperative Deep $Q$-learning Framework for Environments Providing Image Feedback","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2203.08345","title":"Gradient Correction beyond Gradient Descent","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2206.14137","title":"aSTDP: A More Biologically Plausible Learning","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2208.01416","title":"Biologically Plausible Training of Deep Neural Networks Using a Top-down Credit Assignment Network","created":"2022-08-01","cited_by_count":0,"area":null}],"next_cursor":"100"}