English
Related papers

Related papers: Network Transplanting (extended abstract)

200 papers

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…

Machine Learning · Computer Science 2021-03-26 Zhenyan Hou , Wenxuan Fan

End-to-end training with back propagation is the standard method for training deep neural networks. However, as networks become deeper and bigger, end-to-end training becomes more challenging: highly non-convex models gets stuck easily in…

Machine Learning · Computer Science 2020-10-12 Laëtitia Shao , Max Moroz , Elad Eban , Yair Movshovitz-Attias

Knowledge distillation transfers the knowledge from a cumbersome teacher to a small student. Recent results suggest that the student-friendly teacher is more appropriate to distill since it provides more transferable knowledge. In this…

Machine Learning · Computer Science 2022-07-26 Jinhyuk Park , Albert No

Modular neural networks outperform nonmodular neural networks on tasks ranging from visual question answering to robotics. These performance improvements are thought to be due to modular networks' superior ability to model the compositional…

Machine Learning · Computer Science 2025-03-12 Akhilan Boopathy , Sunshine Jiang , William Yue , Jaedong Hwang , Abhiram Iyer , Ila Fiete

After a large "teacher" neural network has been trained on labeled data, the probabilities that the teacher assigns to incorrect classes reveal a lot of information about the way in which the teacher generalizes. By training a small…

Machine Learning · Computer Science 2020-06-12 Rafael Müller , Simon Kornblith , Geoffrey Hinton

Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Mengye Ren , Tyler R. Scott , Michael L. Iuzzolino , Michael C. Mozer , Richard Zemel

This paper proposes network recasting as a general method for network architecture transformation. The primary goal of this method is to accelerate the inference process through the transformation, but there can be many other practical…

Machine Learning · Computer Science 2019-06-20 Joonsang Yu , Sungbum Kang , Kiyoung Choi

Existing subset selection methods for efficient learning predominantly employ discrete combinatorial and model-specific approaches which lack generalizability. For an unseen architecture, one cannot use the subset chosen for a different…

Machine Learning · Computer Science 2024-09-20 Eeshaan Jain , Tushar Nandy , Gaurav Aggarwal , Ashish Tendulkar , Rishabh Iyer , Abir De

It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution…

Machine Learning · Computer Science 2022-06-28 Bruno Casella , Alessio Barbaro Chisari , Sebastiano Battiato , Mario Valerio Giuffrida

Distillation is the task of replacing a complicated machine learning model with a simpler model that approximates the original [BCNM06,HVD15]. Despite many practical applications, basic questions about the extent to which models can be…

Machine Learning · Computer Science 2024-05-07 Enric Boix-Adsera

In this paper, we propose a simple but effective method for training neural networks with a limited amount of training data. Our approach inherits the idea of knowledge distillation that transfers knowledge from a deep or wide reference…

Machine Learning · Statistics 2018-07-06 Akisato Kimura , Zoubin Ghahramani , Koh Takeuchi , Tomoharu Iwata , Naonori Ueda

We introduce techniques for rapidly transferring the information stored in one neural net into another neural net. The main purpose is to accelerate the training of a significantly larger neural net. During real-world workflows, one often…

Machine Learning · Computer Science 2016-04-26 Tianqi Chen , Ian Goodfellow , Jonathon Shlens

Although deep neural networks (DNNs) have demonstrated impressive results during the last decade, they remain highly specialized tools, which are trained -- often from scratch -- to solve each particular task. The human brain, in contrast,…

Neural and Evolutionary Computing · Computer Science 2019-08-22 Alexander V. Terekhov , Guglielmo Montone , J. Kevin O'Regan

Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks. Yet, real-world applications often demand compact models tailored to specific problems. Variants of knowledge distillation have been devised…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Juliette Marrie , Michael Arbel , Julien Mairal , Diane Larlus

Although neural networks are well suited for sequential transfer learning tasks, the catastrophic forgetting problem hinders proper integration of prior knowledge. In this work, we propose a solution to this problem by using a multi-task…

Computation and Language · Computer Science 2017-04-13 Matthew Riemer , Elham Khabiri , Richard Goodwin

Compressing deep networks is essential to expand their range of applications to constrained settings. The need for compression however often arises long after the model was trained, when the original data might no longer be available. On…

Machine Learning · Computer Science 2022-01-19 Jean-Michel Begon , Pierre Geurts

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Syed Shakib Sarwar , Aayush Ankit , Kaushik Roy

Human intelligence is characterized not only by the capacity to learn complex skills, but the ability to rapidly adapt and acquire new skills within an ever-changing environment. In this work we study how the learning of modular solutions…

Machine Learning · Computer Science 2020-10-26 Jianan Wang , Eren Sezener , David Budden , Marcus Hutter , Joel Veness

We present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike…

Biological Physics · Physics 2007-05-23 Hong Zhao , Tao Jin

Methods for learning Bayesian network structure can discover dependency structure between observed variables, and have been shown to be useful in many applications. However, in domains that involve a large number of variables, the space of…

Machine Learning · Computer Science 2012-12-12 Eran Segal , Dana Pe'er , Aviv Regev , Daphne Koller , Nir Friedman