paper-with-me

홈 › Papers

Boosting Network Weight Separability via Feed-Backward Reconstruction

2019-10-20 · Jongmin Yu, Hyeontaek Oh

This paper proposes a new evaluation metric and boosting method for weight separability in neural network design. In contrast to general visual recognition methods designed to encourage both intra-class compactness and inter-class separability of latent features, we focus on estimating linear independence of column vectors in weight matrix and improving the separability of weight vectors. To this end, we propose an evaluation metric for weight separability based on semi-orthogonality of a matrix and Frobenius distance, and the feed-backward reconstruction loss which explicitly encourages weight separability between the column vectors in the weight matrix. The experimental results on image classification and face recognition demonstrate that the weight separability boosting via minimization of feed-backward reconstruction loss can improve the visual recognition performance, hence universally boosting the performance on various visual recognition tasks.

📄 PDF Abstract BibTeX arXiv:1910.09024

Code (0)

등록된 구현이 없습니다.

Tasks

Face Recognitionimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Learning the Connections in Direct Feedback Alignment

2021-01-01 · Matthew Bailey Webster, Jonghyun Choi, changwook Ahn

Feedback alignment was proposed to address the biological implausibility of the backpropagation algorithm which requires the transportation of the weight transpose during the backwards pass. The idea was later built upon…

Image Classification

PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine

2023-08-23 · Chenrui Zhang, Lin Liu, Jinpeng Wang, Chuyuan Wang 외

As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ense…

Ensemble LearningHallucination

NeuralEQ: Neural-Network-Based Equalizer for High-Speed Wireline Communication

2023-08-04 · Hanseok Kim, Jae Hyung Ju, Hyun Seok Choi, Hyeri Roh 외

With the growing demand for high-bandwidth applications like video streaming and cloud services, the data transfer rates required for wireline communication keeps increasing, making the channel loss a major obstacle in a…

Spike-based causal inference for weight alignment

2019-10-03 · ICLR 2020 1 · Jordan Guerguiev, Konrad P. Kording, Blake A. Richards

In artificial neural networks trained with gradient descent, the weights used for processing stimuli are also used during backward passes to calculate gradients. For the real brain to approximate gradients, gradient info…

Causal InferenceEconometrics

Feedforward and Recurrent Neural Networks Backward Propagation and Hessian in Matrix Form

2017-09-16 · Maxim Naumov

In this paper we focus on the linear algebra theory behind feedforward (FNN) and recurrent (RNN) neural networks. We review backward propagation, including backward propagation through time (BPTT). Also, we obtain a new …

Form