paper-with-me

Papers

Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning

2016-10-19 · Qianli Liao, Kenji Kawaguchi, Tomaso Poggio

We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and (2) recurrent learning. Our proposal is simpler and more biologically-plausible. Unlike previous approaches, our technique can be applied out of the box to all learning scenarios (e.g., online learning, batch learning, fully-connected, convolutional, feedforward, recurrent and mixed --- recurrent and convolutional) and compare favorably with existing approaches. We also propose Lp Normalization for normalizing by different orders of statistical moments. In particular, L1 normalization is well-performing, simple to implement, fast to compute, more biologically-plausible and thus ideal for GPU or hardware implementations.

📄 PDF Abstract BibTeX arXiv:1610.06160

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Similar Papers 제목 키워드 기반

A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data

2015-03-02 · Cengiz Pehlevan, Tao Hu, Dmitri B. Chklovskii

Neural network models of early sensory processing typically reduce the dimensionality of streaming input data. Such networks learn the principal subspace, in the sense of principal component analysis (PCA), by adjusting …

Applications of the Free Energy Principle to Machine Learning and Neuroscience

2021-06-30 · Beren Millidge

In this PhD thesis, we explore and apply methods inspired by the free energy principle to two important areas in machine learning and neuroscience. The free energy principle is a general mathematical theory of the necess…

Bayesian InferenceBIG-bench Machine LearningDeep Reinforcement Learning

Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks

2020-06-12 · NeurIPS 2020 12 · Roman Pogodin, Peter E. Latham

The state-of-the art machine learning approach to training deep neural networks, backpropagation, is implausible for real neural networks: neurons need to know their outgoing weights; training alternates between a bottom…

image-classificationImage Classification

A differential Hebbian framework for biologically-plausible motor control

2020-06-24 · Sergio Verduzco-Flores, William Dorrell, Erik DeSchutter

In this paper we explore a neural control architecture that is both biologically plausible, and capable of fully autonomous learning. It consists of feedback controllers that learn to achieve a desired state by selecting…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Memory Networks: Towards Fully Biologically Plausible Learning

2024-09-18 · Jacobo Ruiz, Manas Gupta

The field of artificial intelligence faces significant challenges in achieving both biological plausibility and computational efficiency, particularly in visual learning tasks. Current artificial neural networks, such as…

Computational Efficiency