English
Related papers

Related papers: Tensor Product Representation Probes Reveal Shared…

200 papers

How do sequence models represent their decision-making process? Prior work suggests that Othello-playing neural network learned nonlinear models of the board state (Li et al., 2023). In this work, we provide evidence of a closely related…

Machine Learning · Computer Science 2023-09-11 Neel Nanda , Andrew Lee , Martin Wattenberg

Generating formal-language programs represented by relational tuples, such as Lisp programs or mathematical operations, to solve problems stated in natural language is a challenging task because it requires explicitly capturing discrete…

Computation and Language · Computer Science 2020-08-04 Kezhen Chen , Qiuyuan Huang , Hamid Palangi , Paul Smolensky , Kenneth D. Forbus , Jianfeng Gao

Since the inception of the classicalist vs. connectionist debate, it has been argued that the ability to systematically combine symbol-like entities into compositional representations is crucial for human intelligence. In connectionist…

Machine Learning · Computer Science 2025-01-24 Bethia Sun , Maurice Pagnucco , Yang Song

idely used recurrent units, including Long-short Term Memory (LSTM) and the Gated Recurrent Unit (GRU), perform well on natural language tasks, but their ability to learn structured representations is still questionable. Exploiting reduced…

Neural and Evolutionary Computing · Computer Science 2019-11-06 Shuai Tang , Paul Smolensky , Virginia R. de Sa

Recurrent neural networks (RNNs) can learn continuous vector representations of symbolic structures such as sequences and sentences; these representations often exhibit linear regularities (analogies). Such regularities motivate our…

Computation and Language · Computer Science 2019-03-06 R. Thomas McCoy , Tal Linzen , Ewan Dunbar , Paul Smolensky

This paper proposes a new architecture - Attentive Tensor Product Learning (ATPL) - to represent grammatical structures in deep learning models. ATPL is a new architecture to bridge this gap by exploiting Tensor Product Representations…

Computation and Language · Computer Science 2018-11-30 Qiuyuan Huang , Li Deng , Dapeng Wu , Chang Liu , Xiaodong He

Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process…

Machine Learning · Computer Science 2024-06-27 Kenneth Li , Aspen K. Hopkins , David Bau , Fernanda Viégas , Hanspeter Pfister , Martin Wattenberg

We consider the problem of learning discriminative representations for data in a high-dimensional space with distribution supported on or around multiple low-dimensional linear subspaces. That is, we wish to compute a linear injective map…

Machine Learning · Statistics 2022-10-07 Druv Pai , Michael Psenka , Chih-Yuan Chiu , Manxi Wu , Edgar Dobriban , Yi Ma

In recent research, Tensor Product Representation (TPR) is applied for the systematic generalization task of deep neural networks by learning the compositional structure of data. However, such prior works show limited performance in…

Machine Learning · Computer Science 2024-06-04 Taewon Park , Inchul Choi , Minho Lee

Dimensionality reduction is an effective method for learning high-dimensional data, which can provide better understanding of decision boundaries in human-readable low-dimensional subspace. Linear methods, such as principal component…

Machine Learning · Computer Science 2020-07-09 Koji Maruhashi , Heewon Park , Rui Yamaguchi , Satoru Miyano

The current methods for learning representations with auto-encoders almost exclusively employ vectors as the latent representations. In this work, we propose to employ a tensor product structure for this purpose. This way, the obtained…

Machine Learning · Computer Science 2023-09-01 Michael Rotman , Amit Dekel , Shir Gur , Yaron Oz , Lior Wolf

With the recent success of pre-trained models in NLP, a significant focus was put on interpreting their representations. One of the most prominent approaches is structural probing (Hewitt and Manning, 2019), where a linear projection of…

Computation and Language · Computer Science 2021-06-25 Tomasz Limisiewicz , David Mareček

We introduce an architecture, the Tensor Product Recurrent Network (TPRN). In our application of TPRN, internal representations learned by end-to-end optimization in a deep neural network performing a textual question-answering (QA) task…

Computation and Language · Computer Science 2017-09-27 Hamid Palangi , Paul Smolensky , Xiaodong He , Li Deng

The aim of this work is to study finite dimensional representations of the Lie superalgebra psl(2|2) and their tensor products. In particular, we shall decompose all tensor products involving typical (long) and atypical (short)…

High Energy Physics - Theory · Physics 2007-05-23 Gerhard Gotz , Thomas Quella , Volker Schomerus

This work explores whether language models encode meaningfully grounded representations of sounds of objects. We learn a linear probe that retrieves the correct text representation of an object given a snippet of audio related to that…

Computation and Language · Computer Science 2024-08-19 Jerry Ngo , Yoon Kim

We present a new approach to the design of deep networks for natural language processing (NLP), based on the general technique of Tensor Product Representations (TPRs) for encoding and processing symbol structures in distributed neural…

Computer Vision and Pattern Recognition · Computer Science 2017-12-19 Qiuyuan Huang , Paul Smolensky , Xiaodong He , Li Deng , Dapeng Wu

How do artificial neural networks bind concepts to form complex semantic structures? Here, we propose a simple neural code, whereby the existence and the type of relations between entities are represented by the distance and the direction…

Computation and Language · Computer Science 2026-05-19 Pablo J. Diego-Simón , Pierre Orhan , Emmanuel Chemla , Yair Lakretz , Jean-Rémi King

This paper introduces the Manifold Probe, a supervised method for discovering representation manifolds in superposition. The method generalizes linear regression probes by learning the space of features of a concept that can be linearly…

Machine Learning · Computer Science 2026-05-19 Alexander Modell

Parametric models in vector spaces are shown to possess an associated linear map. This linear operator leads directly to reproducing kernel Hilbert spaces and affine- / linear- representations in terms of tensor products. From the…

Numerical Analysis · Mathematics 2018-06-19 Hermann G. Matthies , Roger Ohayon

Tensor train (TT) decomposition is a powerful representation for high-order tensors, which has been successfully applied to various machine learning tasks in recent years. However, since the tensor product is not commutative, permutation of…

Numerical Analysis · Computer Science 2017-05-31 Qibin Zhao , Masashi Sugiyama , Andrzej Cichocki
‹ Prev 1 2 3 10 Next ›