English
Related papers

Related papers: Decomposing Representation Space into Interpretabl…

200 papers

Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…

Machine Learning · Computer Science 2016-02-09 William Whitney

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Machine Learning · Computer Science 2020-12-08 Isaac Lage , Finale Doshi-Velez

Autoencoders are commonly used in representation learning. They consist of an encoder and a decoder, which provide a straightforward way to map n-dimensional data in input space to a lower m-dimensional representation space and back. The…

Machine Learning · Computer Science 2021-11-16 Viktoria Schuster , Anders Krogh

Constructing good representations is critical for learning complex tasks in a sample efficient manner. In the context of meta-learning, representations can be constructed from common patterns of previously seen tasks so that a future task…

Machine Learning · Computer Science 2021-03-02 Halil Ibrahim Gulluk , Yue Sun , Samet Oymak , Maryam Fazel

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

Machine Learning · Computer Science 2024-11-08 Jacob Dunefsky , Philippe Chlenski , Neel Nanda

Representations pervade our daily experience, from letters representing sounds to bit strings encoding digital files. While such representations require externally defined decoders to convey meaning, conscious experience appears…

Neurons and Cognition · Quantitative Biology 2025-12-15 Francesco Lässig

Unsupervised representation learning has succeeded with excellent results in many applications. It is an especially powerful tool to learn a good representation of environments with partial or noisy observations. In partially observable…

Machine Learning · Computer Science 2019-08-20 Zhaohan Daniel Guo , Mohammad Gheshlaghi Azar , Bilal Piot , Bernardo A. Pires , Rémi Munos

Despite tremendous progress over the past decade, deep learning methods generally fall short of human-level systematic generalization. It has been argued that explicitly capturing the underlying structure of data should allow connectionist…

Machine Learning · Computer Science 2023-04-26 Andrea Dittadi

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of…

Computation and Language · Computer Science 2023-01-10 Zhuosheng Zhang , Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita , Zuchao Li , Hai Zhao

Deep feature spaces have the capacity to encode complex transformations of their input data. However, understanding the relative feature-space relationship between two transformed encoded images is difficult. For instance, what is the…

Computer Vision and Pattern Recognition · Computer Science 2017-10-23 Daniel E. Worrall , Stephan J. Garbin , Daniyar Turmukhambetov , Gabriel J. Brostow

Supervised manifold learning methods learn data representations by preserving the geometric structure of data while enhancing the separation between data samples from different classes. In this work, we propose a theoretical study of…

Machine Learning · Computer Science 2018-01-08 Elif Vural , Christine Guillemot

Although neural networks have seen tremendous success as predictive models in a variety of domains, they can be overly confident in their predictions on out-of-distribution (OOD) data. To be viable for safety-critical applications, like…

Robotics · Computer Science 2022-11-17 Masha Itkina , Mykel J. Kochenderfer

We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model,…

Computer Vision and Pattern Recognition · Computer Science 2017-04-20 David Bau , Bolei Zhou , Aditya Khosla , Aude Oliva , Antonio Torralba

Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the difficulty of…

Computation and Language · Computer Science 2020-04-29 Yau-Shian Wang , Hung-Yi Lee , Yun-Nung Chen

Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each…

Machine Learning · Computer Science 2025-11-18 Leo Gao , Achyuta Rajaram , Jacob Coxon , Soham V. Govande , Bowen Baker , Dan Mossing

We discuss probabilistic neural networks with a fixed internal representation as models for machine understanding. Here understanding is intended as mapping data to an already existing representation which encodes an {\em a priori}…

Disordered Systems and Neural Networks · Physics 2023-12-07 Rongrong Xie , Matteo Marsili

Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where each dimension is inherently interpretable. By inherently…

Computation and Language · Computer Science 2021-09-29 Adly Templeton

Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned parameters are not interpretable. In this paper, we re-examine the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-21 Yinpeng Dong , Hang Su , Jun Zhu , Fan Bao

Dimensionality reduction techniques are fundamental for analyzing and visualizing high-dimensional data. With established methods like t-SNE and PCA presenting a trade-off between representational power and interpretability. This paper…

Machine Learning · Computer Science 2025-04-25 Erik Bergh

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma
‹ Prev 1 4 5 6 7 8 10 Next ›