Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks

• URL: http://arxiv.org/abs/2606.31700v1
• Date: Tue, 30 Jun 2026 14:09:40 GMT
• Title: Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks
• Abstract summary: We introduce modulo error routing to extend Error Diffusion beyond binary classification.<n>We show that a dual-stream excitatory/inhibitory architecture trained with this method achieves 96.7% on MNIST.<n>In reinforcement learning, we integrate ED with Proximal Policy Optimization (PPO) and evaluate it on continuous-control tasks in Google Brax and on Craftax.
• Score: 20.760754362327933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Biological neural circuits obey Dale's principle: each neuron's synapses are uniformly excitatory or inhibitory. Artificial networks that respect this constraint must coordinate separate excitatory and inhibitory populations, fundamentally changing how credit is assigned during learning. Several biologically plausible learning rules avoid backpropagation's weight transport requirement, but it has been difficult to achieve strong performance under Dale's principle beyond MNIST. Error Diffusion (ED) was originally proposed in a dual-stream excitatory/inhibitory architecture, where learning is driven by routing global error signals to all layers without transporting transposed forward weights or relying on random feedback matrices. Whether such a rule can scale under Dale's principle across both supervised classification and reinforcement learning remains unknown. Here, we introduce modulo error routing to extend Error Diffusion beyond binary classification, and show that a dual-stream excitatory/inhibitory architecture trained with this method achieves 96.7% on MNIST and establishes a 61.7% baseline on CIFAR-10, demonstrating that representation learning is possible even when strictly enforcing Dale's principle. For the classification setting, we introduce three domain-specific innovations: layer-specific sigmoid widths, batch-centered class error signals, and asymmetric initialization, and ablation analysis reveals that their relative importance reverses between MNIST and CIFAR-10, exposing task-dependent credit-assignment bottlenecks invisible to single-benchmark evaluation. In reinforcement learning, we integrate ED with Proximal Policy Optimization (PPO) and evaluate it on continuous-control tasks in Google Brax and on Craftax, an open-ended exploration task. We show that ED-PPO achieves competitive performance relative to Direct Feedback Alignment, a backpropagation-free baseline.

Related papers

• Neural-ESO: A Dual-Pathway Architecture for Provably Robust Learning-Based Control [5.565368627826789]
  We present a learning-enabled disturbance-rejection framework based on a Neural Extended State Observer (Neural-ESO)<n>Unlike existing learning-based control methods that largely rely on the learned model once deployed, Neural-ESO adopts a dual-pathway architecture.<n>We show that enforcing a Lipschitz bound on the learning component guarantees uniform ultimate boundedness of the closed-loop error dynamics.
  arXiv  Detail & Related papers  (2026-07-07T17:41:38Z)
• Purified OPSD: On-Policy Self-Distillation Without Losing How to Think [52.879387744920415]
  We find that on-policy self-distillation (OPSD) consistently fails on long chain-of-thought (long-CoT) reasoning models.<n>We propose a two-step solution: first, we construct a reference-only teacher to isolate the non-transferable component of the supervision signal.<n>Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution.
  arXiv  Detail & Related papers  (2026-07-02T14:33:07Z)
• GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs [5.018957704056544]
  Activation steering controls model behavior by modifying intermediate hidden states at inference time without retraining.<n>We show that when multiple semantic directions are superposed without constraints, the model collapses.<n>We propose GEMS, a training-free method that maps each source to a corresponding geometric constraint.
  arXiv  Detail & Related papers  (2026-06-18T08:43:33Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• DIS2: Disentanglement Meets Distillation with Classwise Attention for Robust Remote Sensing Segmentation under Missing Modalities [28.992992584085787]
  DIS2 is a new paradigm shifting from modality-shared feature dependence to active, guided missing features compensation.<n> Compensatory features are explicitly captured which, when fused with the features of the available modality, approximate the ideal fused representation of the full-modality case.<n>Our proposed approach significantly outperforms state-of-the-art methods across benchmarks.
  arXiv  Detail & Related papers  (2026-01-20T01:33:54Z)
• Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy [24.387204607890578]
  Imitation learning (IL) enables autonomous behavior by learning from expert demonstrations.<n>We propose a Layered Control Architecture (LCA) that integrates TaSIL andellonedrac.<n>Our solution paves the path for designing fully certifiable autonomy pipelines.
  arXiv  Detail & Related papers  (2025-12-19T18:58:11Z)
• Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification [59.59359638389348]
  We propose a Dual-level Modality Debiasing Learning framework that implements debiasing at both the model and optimization levels.<n>Experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model.
  arXiv  Detail & Related papers  (2025-12-03T12:43:16Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• ADPS: Asymmetric Distillation Post-Segmentation for Image Anomaly Detection [75.68023968735523]
  Knowledge Distillation-based Anomaly Detection (KDAD) methods rely on the teacher-student paradigm to detect and segment anomalous regions. We propose an innovative approach called Asymmetric Distillation Post-Segmentation (ADPS) Our ADPS employs an asymmetric distillation paradigm that takes distinct forms of the same image as the input of the teacher-student networks. We show that ADPS significantly improves Average Precision (AP) metric by 9% and 20% on the MVTec AD and KolektorSDD2 datasets.
  arXiv  Detail & Related papers  (2022-10-19T12:04:47Z)
• Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass [8.39059551023011]
  Supervised learning in artificial neural networks typically relies on backpropagation. We show that this approach lacks biological plausibility in many regards. We propose to replace the backward pass with a second forward pass in which the input signal is modulated based on the error of the network.
  arXiv  Detail & Related papers  (2022-01-27T17:12:05Z)
• Feature Purification: How Adversarial Training Performs Robust Deep Learning [66.05472746340142]
  We show a principle that we call Feature Purification, where we show one of the causes of the existence of adversarial examples is the accumulation of certain small dense mixtures in the hidden weights during the training process of a neural network. We present both experiments on the CIFAR-10 dataset to illustrate this principle, and a theoretical result proving that for certain natural classification tasks, training a two-layer neural network with ReLU activation using randomly gradient descent indeed this principle.
  arXiv  Detail & Related papers  (2020-05-20T16:56:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.