paper-with-me

홈 › Papers

Learning representations for binary-classification without backpropagation

2020-05-01 · ICLR 2020 1 · Mathias Lechner

The family of feedback alignment (FA) algorithms aims to provide a more biologically motivated alternative to backpropagation (BP), by substituting the computations that are unrealistic to be implemented in physical brains. While FA algorithms have been shown to work well in practice, there is a lack of rigorous theory proofing their learning capabilities. Here we introduce the first feedback alignment algorithm with provable learning guarantees. In contrast to existing work, we do not require any assumption about the size or depth of the network except that it has a single output neuron, i.e., such as for binary classification tasks. We show that our FA algorithm can deliver its theoretical promises in practice, surpassing the learning performance of existing FA methods and matching backpropagation in binary classification tasks. Finally, we demonstrate the limits of our FA variant when the number of output neurons grows beyond a certain quantity.

📄 PDF Abstract BibTeX

Code (1)

mlech26l/iclr_paper_mdfa 공식 구현 tf

Tasks

Binary ClassificationClassificationGeneral Classification

Methods 이 논문이 사용한 방법론

FA 설명 없음

Similar Papers 제목 키워드 기반

Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation

2015-03-12 · Zhiyong Cheng, Daniel Soudry, Zexi Mao, Zhenzhong Lan

Compared to Multilayer Neural Networks with real weights, Binary Multilayer Neural Networks (BMNNs) can be implemented more efficiently on dedicated hardware. BMNNs have been demonstrated to be effective on binary classi…

Binary ClassificationGeneral Classificationimage-classificationImage Classification

An experimental comparative study of backpropagation and alternatives for training binary neural networks for image classification

2024-08-08 · Ben Crulis, Barthelemy Serres, Cyril de Runz, Gilles Venturini

Current artificial neural networks are trained with parameters encoded as floating point numbers that occupy lots of memory space at inference time. Due to the increase in the size of deep learning models, it is becoming…

image-classificationImage Classification

Chi-Square Test Neural Network: A New Binary Classifier based on Backpropagation Neural Network

2018-09-04 · Yuan Wu, Lingling Li, Lian Li

We introduce the chi-square test neural network: a single hidden layer backpropagation neural network using chi-square test theorem to redefine the cost function and the error function. The weights and thresholds are mod…

Binary ClassificationClassificationGeneral Classification

Hardware-efficient on-line learning through pipelined truncated-error backpropagation in binary-state networks

2017-06-15 · Hesham Mostafa, Bruno Pedroni, Sadique Sheik, Gert Cauwenberghs

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing…

Self-Binarizing Networks

2019-02-02 · Fayez Lahoud, Radhakrishna Achanta, Pablo Márquez-Neila, Sabine Süsstrunk

We present a method to train self-binarizing neural networks, that is, networks that evolve their weights and activations during training to become binary. To obtain similar binary networks, existing methods rely on the …

Binarization