English
Related papers

Related papers: Succinct Representations for Concepts

200 papers

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

Machine Learning · Computer Science 2018-03-14 Osbert Bastani , Carolyn Kim , Hamsa Bastani

How can we discover and succinctly summarize the concepts that a neural network has learned? Such a task is of great importance in applications of networks in areas of inference that involve classification, like medical diagnosis based on…

Machine Learning · Computer Science 2020-12-24 Uday Singh Saini , Evangelos E. Papalexakis

We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive…

Computer Vision and Pattern Recognition · Computer Science 2018-02-21 Oisin Mac Aodha , Shihan Su , Yuxin Chen , Pietro Perona , Yisong Yue

The quality of learned features by representation learning determines the performance of learning algorithms and the related application tasks (such as high-dimensional data clustering). As a relatively new paradigm for representation…

Machine Learning · Computer Science 2021-02-02 Zhao Zhang , Yan Zhang , Mingliang Xu , Li Zhang , Yi Yang , Shuicheng Yan

Since early machine learning models, metrics such as accuracy and precision have been the de facto way to evaluate and compare trained models. However, a single metric number doesn't fully capture the similarities and differences between…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Ahmad Mustapha , Wael Khreich , Wes Masri

In this case study, we explore the capabilities and limitations of ChatGPT, a natural language processing model developed by OpenAI, in the field of string theoretical swampland conjectures. We find that it is effective at paraphrasing and…

Popular Physics · Physics 2023-01-20 Kay Lehnert

We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Zhonghao Wang , Kai Wang , Mo Yu , Jinjun Xiong , Wen-mei Hwu , Mark Hasegawa-Johnson , Humphrey Shi

While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…

Computation and Language · Computer Science 2016-08-23 Jifan Chen , Kan Chen , Xipeng Qiu , Qi Zhang , Xuanjing Huang , Zheng Zhang

Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to…

Computation and Language · Computer Science 2021-09-14 Xiongyi Zhang , Jan-Willem van de Meent , Byron C. Wallace

Automated decision making is often complicated by the complexity of the knowledge involved. Much of this complexity arises from the context sensitive variations of the underlying phenomena. We propose a framework for representing…

Artificial Intelligence · Computer Science 2013-03-25 Tze-Yun Leong

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Hila Chefer , Oran Lang , Mor Geva , Volodymyr Polosukhin , Assaf Shocher , Michal Irani , Inbar Mosseri , Lior Wolf

Patterns are fundamental to human cognition, enabling the recognition of structure and regularity across diverse domains. In this work, we focus on structural repeats, patterns that arise from the repetition of hierarchical relations within…

Computation and Language · Computer Science 2025-04-15 Zeng Ren , Xinyi Guan , Martin Rohrmeier

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…

Machine Learning · Computer Science 2022-04-05 Pedro Sandoval-Segura , Wallace Lawson

Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level parts that can be matched and compared across different…

Machine Learning · Computer Science 2026-05-19 Phu-Quy Nguyen-Lam , Phu-Hoa Pham , Dao Sy Duy Minh , Chi-Nguyen Tran , Huynh Trung Kiet , Long Tran-Thanh

Neural networks deliver impressive predictive performance across a variety of tasks, but they are often opaque in their decision-making processes. Despite a growing interest in mechanistic interpretability, tools for systematically…

Machine Learning · Computer Science 2026-04-09 Ricardo Knauer , Andre Beinrucker , Erik Rodner

The effectiveness of in-context learning relies heavily on selecting demonstrations that provide all the necessary information for a given test input. To achieve this, it is crucial to identify and cover fine-grained knowledge requirements.…

Computation and Language · Computer Science 2025-09-17 Wonbin Kweon , SeongKu Kang , Runchu Tian , Pengcheng Jiang , Jiawei Han , Hwanjo Yu

While many methods for learning vector space embeddings have been proposed in the field of Natural Language Processing, these methods typically do not distinguish between categories and individuals. Intuitively, if individuals are…

Computation and Language · Computer Science 2019-12-04 Zied Bouraoui , Jose Camacho-Collados , Luis Espinosa-Anke , Steven Schockaert

Concept Bottleneck Models (CBMs) are regarded as inherently interpretable because they first predict a set of human-defined concepts which are used to predict a task label. For inherent interpretability to be fully realised, and ensure…

Machine Learning · Computer Science 2024-07-31 Jack Furby , Daniel Cunnington , Dave Braines , Alun Preece

The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can…

Machine Learning · Statistics 2016-07-04 Nick Condry

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal…

Artificial Intelligence · Computer Science 2018-05-10 Vitalii Zhelezniak , Dan Busbridge , April Shen , Samuel L. Smith , Nils Y. Hammerla