English
Related papers

Related papers: Constraining Representations Yields Models That Kn…

200 papers

Predictive Coding Networks (PCNs) aim to learn a generative model of the world. Given observations, this generative model can then be inverted to infer the causes of those observations. However, when training PCNs, a noticeable pathology is…

Artificial Intelligence · Computer Science 2022-09-02 Paul F Kinghorn , Beren Millidge , Christopher L Buckley

Despite tremendous success of modern neural networks, they are known to be overconfident even when the model encounters inputs with unfamiliar conditions. Detecting such inputs is vital to preventing models from making naive predictions…

Computer Vision and Pattern Recognition · Computer Science 2020-09-07 Jinsol Lee , Ghassan AlRegib

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…

Computer Science and Game Theory · Computer Science 2016-11-29 Bo Li , Yevgeniy Vorobeychik , Xinyun Chen

While being very successful in solving many downstream tasks, the application of deep neural networks is limited in real-life scenarios because of their susceptibility to domain shifts such as common corruptions, and adversarial attacks.…

Machine Learning · Computer Science 2025-03-14 Tejaswini Medi , Julia Grabinski , Margret Keuper

Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events'…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Fabio Valerio Massoli , Fabrizio Falchi , Alperen Kantarci , Şeymanur Akti , Hazim Kemal Ekenel , Giuseppe Amato

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

We present techniques for automatically inferring formal properties of feed-forward neural networks. We observe that a significant part (if not all) of the logic of feed forward networks is captured in the activation status ('on' or 'off')…

Machine Learning · Computer Science 2020-09-14 Divya Gopinath , Hayes Converse , Corina S. Pasareanu , Ankur Taly

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Machine Learning · Computer Science 2024-01-17 Sungmin Cha , Sungjun Cho , Dasol Hwang , Honglak Lee , Taesup Moon , Moontae Lee

Deep neural networks have significantly contributed to the success in predictive accuracy for classification tasks. However, they tend to make over-confident predictions in real-world settings, where domain shifting and out-of-distribution…

Artificial Intelligence · Computer Science 2021-07-16 Yibo Hu , Latifur Khan

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Computation and Language · Computer Science 2021-09-23 Zichao Li , Dheeraj Mekala , Chengyu Dong , Jingbo Shang

Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a…

Machine Learning · Computer Science 2021-09-14 Khashayar Namdar , Masoom A. Haider , Farzad Khalvati

AI deployed in many real-world use cases should be capable of adapting to novelties encountered after deployment. Here, we consider a challenging, under-explored and realistic continual adaptation problem: a deployed AI agent is…

Machine Learning · Computer Science 2024-12-16 Amanda Rios , Ibrahima Ndiour , Parual Datta , Jerry Sydir , Omesh Tickoo , Nilesh Ahuja

The inability of artificial neural networks to assess the uncertainty of their predictions is an impediment to their widespread use. We distinguish two types of learnable uncertainty: model uncertainty due to a lack of training data and…

Machine Learning · Computer Science 2022-06-14 Hans Weytjens , Jochen De Weerdt

Validation accuracy is a necessary, but not sufficient, measure of a neural network classifier's quality. High validation accuracy during development does not guarantee that a model is free of serious flaws, such as vulnerability to…

Machine Learning · Computer Science 2019-10-08 John S. Hyatt , Michael S. Lee

Robots interacting with humans must not only generate learned movements in real-time, but also infer the intent behind observed behaviors and estimate the confidence of their own inferences. This paper proposes a unified model that achieves…

Robotics · Computer Science 2026-03-05 Hiroki Sawada , Alexandre Pitti , Mathias Quoy

Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional…

Computation and Language · Computer Science 2018-02-16 Kalpesh Krishna , Liang Lu , Kevin Gimpel , Karen Livescu

Despite recent progress, deep neural networks generally continue to be vulnerable to so-called adversarial examples--input images with small perturbations that can result in changes in the output classifications, despite no such change in…

Computer Vision and Pattern Recognition · Computer Science 2020-02-25 Matthew J. Roos

Continual learning (CL) over non-stationary data streams remains one of the long-standing challenges in deep neural networks (DNNs) as they are prone to catastrophic forgetting. CL models can benefit from self-supervised pre-training as it…

Machine Learning · Computer Science 2022-07-14 Prashant Bhat , Bahram Zonooz , Elahe Arani

Often in language and other areas of cognition, whether two components of an object are identical or not determines if it is well formed. We call such constraints identity effects. When developing a system to learn well-formedness from…

Machine Learning · Computer Science 2022-03-03 S. Brugiapaglia , M. Liu , P. Tupper

Deep learning opacity often impedes deployment in high-stakes domains. We propose a training framework that aligns model focus with class-representative features without requiring pixel-level annotations. To this end, we introduce…

Artificial Intelligence · Computer Science 2026-02-16 Giacomo Ignesti , Davide Moroni , Massimo Martinelli