English
Related papers

Related papers: For Manifold Learning, Deep Neural Networks can be…

200 papers

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to…

Artificial Intelligence · Computer Science 2018-01-03 Christopher Grimm , Dilip Arumugam , Siddharth Karamcheti , David Abel , Lawson L. S. Wong , Michael L. Littman

Contrastive learning is a representational learning paradigm in which a neural network maps data elements to feature vectors. It improves the feature space by forming lots with an anchor and examples that are either positive or negative…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Fabian Deuser , Philipp Hausenblas , Hannah Schieber , Daniel Roth , Martin Werner , Norbert Oswald

We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation…

Machine Learning · Computer Science 2018-11-27 Chih-Kuan Yeh , Joon Sik Kim , Ian E. H. Yen , Pradeep Ravikumar

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Machine Learning · Computer Science 2021-03-01 Shohei Kubota , Hideaki Hayashi , Tomohiro Hayase , Seiichi Uchida

Deep neural networks have achieved remarkable success, yet our understanding of how they learn remains limited. These models can learn high-dimensional tasks, which is generally statistically intractable due to the curse of dimensionality.…

Machine Learning · Computer Science 2025-10-08 Alessandro Favero

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

We present a set of experiments to demonstrate that deep recurrent neural networks (RNNs) learn internal representations that capture soft hierarchical notions of syntax from highly varied supervision. We consider four syntax tasks at…

Computation and Language · Computer Science 2018-05-14 Terra Blevins , Omer Levy , Luke Zettlemoyer

Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose…

Machine Learning · Computer Science 2018-02-13 Fengwei Zhou , Bin Wu , Zhenguo Li

Deep learning is also known as hierarchical learning, where the learner _learns_ to represent a complicated target function by decomposing it into a sequence of simpler functions to reduce sample and time complexity. This paper formally…

Machine Learning · Computer Science 2023-07-10 Zeyuan Allen-Zhu , Yuanzhi Li

Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such networks follows mostly the supervised learning…

Machine Learning · Computer Science 2015-06-22 Alexey Dosovitskiy , Philipp Fischer , Jost Tobias Springenberg , Martin Riedmiller , Thomas Brox

The present phase of Machine Learning is characterized by supervised learning algorithms relying on large sets of labeled examples ($n \to \infty$). The next phase is likely to focus on algorithms capable of learning from very few labeled…

Computer Vision and Pattern Recognition · Computer Science 2014-03-12 Fabio Anselmi , Joel Z. Leibo , Lorenzo Rosasco , Jim Mutch , Andrea Tacchetti , Tomaso Poggio

Most existing feature learning methods optimize inflexible handcrafted features and the affinity matrix is constructed by shallow linear embedding methods. Different from these conventional methods, we pretrain a generative neural network…

Computer Vision and Pattern Recognition · Computer Science 2019-10-02 Changlu Chen , Chaoxi Niu , Xia Zhan , Kun Zhan

In lifelong learning, tasks (or classes) to be learned arrive sequentially over time in arbitrary order. During training, knowledge from previous tasks can be captured and transferred to subsequent ones to improve sample efficiency. We…

Machine Learning · Computer Science 2022-03-02 Xinyuan Cao , Weiyang Liu , Santosh S. Vempala

Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the input, logit, and label levels have been systematically studied, the intermediate…

Machine Learning · Computer Science 2026-05-29 Hua Li

Non-linear manifold learning enables high-dimensional data analysis, but requires out-of-sample-extension methods to process new data points. In this paper, we propose a manifold learning algorithm based on deep learning to create an…

Machine Learning · Statistics 2015-06-26 Gal Mishne , Uri Shaham , Alexander Cloninger , Israel Cohen

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-02-10 Sayed Hashim , Muhammad Ali

Manifold learning flows are a class of generative modelling techniques that assume a low-dimensional manifold description of the data. The embedding of such a manifold into the high-dimensional space of the data is achieved via learnable…

Machine Learning · Statistics 2025-03-07 Kyriakos Flouris , Ender Konukoglu

Learning based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these methods are designed to generate binary codes that preserve the…

Machine Learning · Computer Science 2016-11-17 Fumin Shen , Chunhua Shen , Qinfeng Shi , Anton van den Hengel , Zhenmin Tang

Representing a manifold of very high-dimensional data with generative models has been shown to be computationally efficient in practice. However, this requires that the data manifold admits a global parameterization. In order to represent…

Machine Learning · Computer Science 2024-08-13 Giovanni S. Alberti , Johannes Hertrich , Matteo Santacesaria , Silvia Sciutto

Matrix completion has received vast amount of attention and research due to its wide applications in various study fields. Existing methods of matrix completion consider only nonlinear (or linear) relations among entries in a data matrix…

Machine Learning · Computer Science 2021-07-16 Saeid Mehrdad , Mohammad Hossein Kahaei