English
Related papers

Related papers: Information Dropout: Learning Optimal Representati…

200 papers

Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much…

Computation and Language · Computer Science 2021-06-14 Yufan Huang , Yanzhe Zhang , Jiaao Chen , Xuezhi Wang , Diyi Yang

Approximate inference in Bayesian deep networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability. We tackle this challenge by introducing a novel…

Machine Learning · Computer Science 2021-11-01 Son Nguyen , Duong Nguyen , Khai Nguyen , Khoat Than , Hung Bui , Nhat Ho

We introduce Noise Injection Node Regularization (NINR), a method of injecting structured noise into Deep Neural Networks (DNN) during the training stage, resulting in an emergent regularizing effect. We present theoretical and empirical…

Machine Learning · Computer Science 2023-05-03 Noam Levi , Itay M. Bloch , Marat Freytsis , Tomer Volansky

Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone…

Machine Learning · Computer Science 2022-10-04 Jirong Yi , Qiaosheng Zhang , Zhen Chen , Qiao Liu , Wei Shao

Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regularization in the point cloud domain is rarely exploited, and most…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Xiao Zang , Yi Xie , Siyu Liao , Jie Chen , Bo Yuan

Despite the popularity and success of deep learning, there is limited understanding of when, how, and why neural networks generalize to unseen examples. Since learning can be seen as extracting information from data, we formally study…

Machine Learning · Computer Science 2023-06-29 Hrayr Harutyunyan

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First,…

Machine Learning · Computer Science 2020-08-10 Rana Ali Amjad , Bernhard C. Geiger

Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent advances in generative modeling have introduced new…

Machine Learning · Computer Science 2026-05-12 Jinjin Chi , Taoping Liu , Mengtao Yin , Ximing Li , Yongcheng Jing , Jialie Shen , Leszek Rutkowski , Dacheng Tao

Representation learning aims to extract meaningful lower-dimensional embeddings from data, known as representations. Despite its widespread application, there is no established definition of a ``good'' representation. Typically, the…

Machine Learning · Computer Science 2024-12-05 Mahalakshmi Sabanayagam , Omar Al-Dabooni , Pascal Esser

In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction of structural representations from data samples. However, conventional task-specific…

Machine Learning · Computer Science 2026-04-21 Zhuojun Tian , Chaouki Ben Issaid , Mehdi Bennis

Regularization is essential for avoiding over-fitting to training data in network optimization, leading to better generalization of the trained networks. The label noise provides a strong implicit regularization by replacing the target…

Machine Learning · Computer Science 2022-05-04 Kensuke Nakamura , Bong-Soo Sohn , Kyoung-Jae Won , Byung-Woo Hong

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing…

Machine Learning · Computer Science 2022-02-18 Mengyue Yang , Xinyu Cai , Furui Liu , Xu Chen , Zhitang Chen , Jianye Hao , Jun Wang

Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we…

Machine Learning · Statistics 2018-07-16 Adji B. Dieng , Rajesh Ranganath , Jaan Altosaar , David M. Blei

Dropout is commonly used to help reduce overfitting in deep neural networks. Sparsity is a potentially important property of neural networks, but is not explicitly controlled by Dropout-based regularization. In this work, we propose…

Machine Learning · Computer Science 2019-04-18 Najeeb Khan , Ian Stavness

Evolutionary computation can be used to optimize several different aspects of neural network architectures. For instance, the TaylorGLO method discovers novel, customized loss functions, resulting in improved performance, faster training,…

Machine Learning · Computer Science 2025-06-12 Santiago Gonzalez , Xin Qiu , Risto Miikkulainen

Dropout has proven to be an effective technique for regularization and preventing the co-adaptation of neurons in deep neural networks (DNN). It randomly drops units with a probability $p$ during the training stage of DNN. Dropout also…

Machine Learning · Computer Science 2018-08-30 Zongjie Ma , Abdul Sattar , Jun Zhou , Qingliang Chen , Kaile Su

We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information…

Machine Learning · Computer Science 2021-07-19 Yann Dubois , Douwe Kiela , David J. Schwab , Ramakrishna Vedantam

We design and analyze a new paradigm for building supervised learning networks, driven only by local optimization rules without relying on a global error function. Traditional neural networks with a fixed topology are made up of identical…

Adaptation and Self-Organizing Systems · Physics 2024-10-04 S. Barland , L. Gil

It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch. Thus, robust representation…

Machine Learning · Computer Science 2020-04-28 Zhengming Ding , Ming Shao , Handong Zhao , Sheng Li

Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away…

Machine Learning · Computer Science 2019-09-10 Aidan N. Gomez , Ivan Zhang , Siddhartha Rao Kamalakara , Divyam Madaan , Kevin Swersky , Yarin Gal , Geoffrey E. Hinton
‹ Prev 1 8 9 10 Next ›