English
Related papers

Related papers: Learning Compositional Latent Structure with Vecto…

200 papers

Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We present a novel RvNN architecture that can provide dynamic…

Computation and Language · Computer Science 2018-11-27 Taeuk Kim , Jihun Choi , Daniel Edmiston , Sanghwan Bae , Sang-goo Lee

Complex visual scenes that are composed of multiple objects, each with attributes, such as object name, location, pose, color, etc., are challenging to describe in order to train neural networks. Usually,deep learning networks are trained…

Neural and Evolutionary Computing · Computer Science 2023-03-27 E. Paxon Frady , Spencer Kent , Quinn Tran , Pentti Kanerva , Bruno A. Olshausen , Friedrich T. Sommer

We describe a basic correspondence between linear algebraic structures within vector embeddings in artificial neural networks and conditional independence constraints on the probability distributions modeled by these networks. Our framework…

Machine Learning · Computer Science 2024-07-15 Matthew Trager , Alessandro Achille , Pramuditha Perera , Luca Zancato , Stefano Soatto

The deep Convolutional Neural Network (CNN) is the state-of-the-art solution for large-scale visual recognition. Following basic principles such as increasing the depth and constructing highway connections, researchers have manually…

Computer Vision and Pattern Recognition · Computer Science 2017-03-07 Lingxi Xie , Alan Yuille

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated…

Machine Learning · Computer Science 2021-10-27 Mike Wu , Noah Goodman , Stefano Ermon

Neural Networks sequentially build high-level features through their successive layers. We propose here a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer,…

Machine Learning · Computer Science 2014-10-03 Ludovic Denoyer , Patrick Gallinari

Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared…

Artificial Intelligence · Computer Science 2018-07-27 Adam Liška , Germán Kruszewski , Marco Baroni

Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented…

Computation and Language · Computer Science 2021-10-20 Yen-Ling Kuo , Boris Katz , Andrei Barbu

The main success stories of deep learning, starting with ImageNet, depend on deep convolutional networks, which on certain tasks perform significantly better than traditional shallow classifiers, such as support vector machines, and also…

Machine Learning · Computer Science 2021-03-26 Arturo Deza , Qianli Liao , Andrzej Banburski , Tomaso Poggio

Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network…

Machine Learning · Computer Science 2021-02-03 Claudio Gallicchio , Simone Scardapane

Convolutional neural networks (CNN's) are powerful and widely used tools. However, their interpretability is far from ideal. One such shortcoming is the difficulty of deducing a network's ability to generalize to unseen data. We use…

Computer Vision and Pattern Recognition · Computer Science 2019-10-21 Rickard Brüel Gabrielsson , Gunnar Carlsson

Existing techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account for the fact that the individual feature channels can…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Seungryong Kim , Sabine Süsstrunk , Mathieu Salzmann

The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks. However, these architectures are rather shallow in comparison to the deep convolutional networks which have…

Computation and Language · Computer Science 2017-01-30 Alexis Conneau , Holger Schwenk , Loïc Barrault , Yann Lecun

We propose a neural embedding algorithm called Network Vector, which learns distributed representations of nodes and the entire networks simultaneously. By embedding networks in a low-dimensional space, the algorithm allows us to compare…

Social and Information Networks · Computer Science 2017-09-11 Hao Wu , Kristina Lerman

Recursive Neural Networks (RvNNs), which compose sequences according to their underlying hierarchical syntactic structure, have performed well in several natural language processing tasks compared to similar models without structural…

Computation and Language · Computer Science 2021-06-14 Jishnu Ray Chowdhury , Cornelia Caragea

We introduce compositional tensor trains (CTTs) for the approximation of multivariate functions, a class of models obtained by composing low-rank functions in the tensor-train format. This format can encode standard approximation tools,…

Numerical Analysis · Mathematics 2025-12-23 Martin Eigel , Charles Miranda , Anthony Nouy , David Sommer

We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images. The building blocks are binary features defined…

Machine Learning · Computer Science 2017-10-27 Miguel Lázaro-Gredilla , Yi Liu , D. Scott Phoenix , Dileep George

We approach structured output prediction by optimizing a deep value network (DVN) to precisely estimate the task loss on different output configurations for a given input. Once the model is trained, we perform inference by gradient descent…

Machine Learning · Computer Science 2017-08-09 Michael Gygli , Mohammad Norouzi , Anelia Angelova

We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures that rely on vector representations. We consider matrices as…

Machine Learning · Computer Science 2018-02-06 Kien Do , Truyen Tran , Svetha Venkatesh

This paper investigates efficient deep neural networks (DNNs) to replace dense unstructured weight matrices with structured ones that possess desired properties. The challenge arises because the optimal weight matrix structure in popular…

Machine Learning · Computer Science 2024-03-11 Changwoo Lee , Hun-Seok Kim