Biological neural networks learn complex behaviors from sparse, delayed feedback using local synaptic plasticity, yet the mechanisms enabling structured credit assignment remain elusive. In contrast, artificial recurrent networks solving similar tasks typically rely on biologically implausible global learning rules or hand-crafted local updates. The space of local plasticity rules capable of supporting learning from delayed reinforcement remains largely unexplored. Here, we present a meta-learning framework that discovers local learning rules for structured credit assignment in recurrent networks trained with sparse feedback. Our approach interleaves local neo-Hebbian-like updates during task execution with an outer loop that optimizes plasticity parameters via \textbf{tangent-propagation through learning}. The resulting three-factor learning rules enable long-timescale credit assignment using only local information and delayed rewards, offering new insights into biologically grounded mechanisms for learning in recurrent circuits.
The cortex learns to make associations between stimuli and spiking activity which supports behaviour. It does this by adjusting synaptic weights. The complexity of these transformations implies that synapses have to change without access to the full error information, a problem typically referred to as "credit-assignment". However, it remains unknown how the cortex solves this problem. We propose that a combination of plasticity rules, 1) Hebbian, 2) acetylcholine-dependent and 3) noradrenaline-dependent excitatory plasticity, together with 4) inhibitory plasticity restoring E/I balance, effec…
Victoria University of Wellington（惠灵顿维多利亚大学）；ETH Zurich（苏黎世联邦理工学院）
Error backpropagation is an extremely effective algorithm for assigning credit in artificial neural networks. However, weight updates under Backprop depend on lengthy recursive computations and require separate output and error messages -- features not shared by biological neurons, that are perhaps unnecessary. In this paper, we revisit Backprop and the credit assignment problem. We first decompose Backprop into a collection of interacting learning algorithms; provide regret bounds on the performance of these sub-algorithms; and factorize Backprop's error signals. Using these results, we deriv…
Credit Assignment via Neural Manifold Noise Correlation
Howard Hughes Medical Institute（霍华德·休斯医学研究所）；Department of Neurobiology, Harvard Medical School（哈佛医学院神经生物学系）；Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University（哈佛大学自然与人工智能研究所在）
Recurrent neural networks are widely used for modeling spatio-temporal sequences in both nature language processing and neural population dynamics. However, understanding the temporal credit assignment is hard. Here, we propose that each individual connection in the recurrent computation is modeled by a spike and slab distribution, rather than a precise weight value. We then derive the mean-field algorithm to train the network at the ensemble level. The method is then applied to classify handwritten digits when pixels are read in sequence, and to the multisensory integration task that is a fun…
PMI Lab, School of Physics, Sun Yat-sen University（中山大学物理学院PMI实验室）
Deep learning has achieved impressive prediction accuracies in a variety of scientific and industrial domains. However, the nested non-linear feature of deep learning makes the learning highly non-transparent, i.e., it is still unknown how the learning coordinates a huge number of parameters to achieve a decision making. To explain this hierarchical credit assignment, we propose a mean-field learning model by assuming that an ensemble of sub-networks, rather than a single network, are trained for a classification task. Surprisingly, our model reveals that apart from some deterministic synaptic…
Animal brains evolved to optimize behavior in dynamically changing environments, selecting actions that maximize future rewards. A large body of experimental work indicates that such optimization changes the wiring of neural circuits, appropriately mapping environmental input onto behavioral outputs. A major unsolved scientific question is how optimal wiring adjustments, which must target the connections responsible for rewards, can be accomplished when the relation between sensory inputs, action taken, environmental context with rewards is ambiguous. The computational problem of properly targ…
Backpropagation (BP) uses detailed, unit-specific feedback to train deep neural networks (DNNs) with remarkable success. That biological neural circuits appear to perform credit assignment, but cannot implement BP, implies the existence of other powerful learning algorithms. Here, we explore the extent to which a globally broadcast learning signal, coupled with local weight updates, enables training of DNNs. We present both a learning rule, called global error-vector broadcasting (GEVB), and a class of DNNs, called vectorized nonnegative networks (VNNs), in which this learning rule operates. V…
Champalimaud Research（尚帕利莫研究中心）；Champalimaud Centre for the Unknown（尚帕利莫未知中心）
Learning depends on changes in synaptic connections deep inside the brain. In multilayer networks, these changes are triggered by error signals fed back from the output, generally through a stepwise inversion of the feedforward processing steps. The gold standard for this process -- backpropagation -- works well in artificial neural networks, but is biologically implausible. Several recent proposals have emerged to address this problem, but many of these biologically-plausible schemes are based on learning an independent set of feedback connections. This complicates the assignment of errors to…
To learn useful dynamics on long time scales, neurons must use plasticity rules that account for long-term, circuit-wide effects of synaptic changes. In other words, neural circuits must solve a credit assignment problem to appropriately assign responsibility for global network behavior to individual circuit components. Furthermore, biological constraints demand that plasticity rules are spatially and temporally local; that is, synaptic changes can depend only on variables accessible to the pre- and postsynaptic neurons. While artificial intelligence offers a computational solution for credit …
Backpropagation is driving today's artificial neural networks (ANNs). However, despite extensive research, it remains unclear if the brain implements this algorithm. Among neuroscientists, reinforcement learning (RL) algorithms are often seen as a realistic alternative: neurons can randomly introduce change, and use unspecific feedback signals to observe their effect on the cost and thus approximate their gradient. However, the convergence rate of such learning scales poorly with the number of involved neurons. Here we propose a hybrid learning approach. Each neuron uses an RL-type strategy to…
Shunting Inhibition and Dendritic Branching Shape Local Credit Assignment
Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University（哈佛大学自然与人工智能研究肯普纳研究所）；Department of Neurobiology, Howard Hughes Medical Institute, Harvard Medical School（哈佛医学院神经生物学系霍华德休斯医学研究所）
