paper-with-me

Papers

A sparse code increases the speed and efficiency of neuro-dynamic programming for optimal control tasks with correlated inputs

2020-06-22 · Peter N. Loxley

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.

📄 PDF Abstract BibTeX arXiv:2006.11968

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Sparse Expansion and Neuronal Disentanglement

2024-05-24 · Shashata Sawmya, Linghao Kong, Ilia Markov, Dan Alistarh 외

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 …

Disentanglement

DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction

2025-08-25 · Weilin Cai, Le Qin, Shwai He, Junwei Cui 외 arxiv

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

2025-03-23 · Roberto Garcia, Jerry Liu, Daniel Sorvisto, Sabri Eyuboglu

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

2026-02-05 · Lixuan Guo, Yifei Wang, Tiansheng Wen, Yifan Wang 외 arxiv

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 Learning

Complexity and Diversity in Sparse Code Priors Improve Receptive Field Characterization of Macaque V1 Neurons

2019-11-19 · Ziniu Wu, Harold Rockwell, Yimeng Zhang, Shiming Tang 외

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