A sparse code increases the speed and efficiency of neuro-dynamic programming for optimal control tasks with correlated inputs
Sparse codes in neuroscience have been suggested to offer certain computational advantages over other neural representations of sensory data. To explore this viewpoint, a sparse code is used to represent natural images in an optimal control task solved with neuro-dynamic programming, and its computational properties are investigated. The central finding is that when feature inputs to a linear network are correlated, an over-complete sparse code increases the memory capacity of the network in an efficient manner beyond that possible for any complete code with the same-sized input, and also increases the speed of learning the network weights. A complete sparse code is found to maximise the memory capacity of a linear network by decorrelating its feature inputs to transform the design matrix of the least-squares problem to one of full rank. It also conditions the Hessian matrix of the least-squares problem, thereby increasing the rate of convergence to the optimal network weights. Other types of decorrelating codes would also achieve this. However, an over-complete sparse code is found to be approximately decorrelated, extracting a larger number of approximately decorrelated features from the same-sized input, allowing it to efficiently increase memory capacity beyond that possible for any complete code: a 2.25 times over-complete sparse code is shown to at least double memory capacity compared with a complete sparse code using the same input. This is used in sequential learning to store a potentially large number of optimal control tasks in the network, while catastrophic forgetting is avoided using a partitioned representation, yielding a cost-to-go function approximator that generalizes over the states in each partition. Sparse code advantages over dense codes and local codes are also discussed.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sparse Expansion and Neuronal Disentanglement
We show how to improve the inference efficiency of an LLM by expanding it into a mixture of sparse experts, where each expert is a copy of the original weights, one-shot pruned for a specific cluster of input values. We …
DisentanglementDualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forwar…
Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters
Large Language Models (LLMs) are computationally intensive, particularly during inference. Neuron-adaptive techniques, which selectively activate neurons in Multi-Layer Perceptron (MLP) layers, offer some speedups but su…
CSRv2: Unlocking Ultra-Sparse Embeddings
In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance and overall system capability. Yet widely used dense embeddings are often extremely high-di…
Representation LearningComplexity and Diversity in Sparse Code Priors Improve Receptive Field Characterization of Macaque V1 Neurons
System identification techniques -- projection pursuit regression models (PPRs) and convolutional neural networks (CNNs) -- provide state-of-the-art performance in predicting visual cortical neurons' responses to arbitra…
Diversity