Related papers: Memory Wrap: a Data-Efficient and Interpretable Ex…

Despite the empirical advances of deep learning across a variety of learning tasks, our theoretical understanding of its success is still very restricted. One of the key challenges is the overparametrized nature of modern models, enabling…

We study utilizing auxiliary information in training data to improve the trustworthiness of machine learning models. Specifically, in the context of image classification, we propose to optimize a training objective that incorporates…

Deep neural networks have revolutionized numerous research fields and applications. Despite their widespread success, a fundamental limitation known as catastrophic forgetting remains, where models fail to retain their ability to perform…

Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions. Temporally- and spatially-consistent, long-term world…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, such as language modelling, this can become a performance…

The wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos' racist image recognition algorithm; thus, necessitated the utilization of the…

In this paper, we introduce a novel framework for memory-efficient and privacy-preserving continual learning in 3D object classification. Unlike conventional memory-based approaches in continual learning that require storing numerous…

Image classification is a fundamental computer vision task and an important baseline for deep metric learning. In decades efforts have been made on enhancing image classification accuracy by using deep learning models while less attention…

With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-hoc analysis, such as explaining how predictions are made or…

This paper designs and implements an explainable recommendation model that integrates knowledge graphs with structure-aware attention mechanisms. The model is built on graph neural networks and incorporates a multi-hop neighbor aggregation…

Self-attention networks have shown remarkable progress in computer vision tasks such as image classification. The main benefit of the self-attention mechanism is the ability to capture long-range feature interactions in attention-maps.…

Digital mammography is essential to breast cancer detection, and deep learning offers promising tools for faster and more accurate mammogram analysis. In radiology and other high-stakes environments, uninterpretable ("black box") deep…

Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learned information upon learning new tasks where previous data is…

Despite the state-of-the-art performance of deep convolutional neural networks, they are susceptible to bias and malfunction in unseen situations. Moreover, the complex computation behind their reasoning is not human-understandable to…

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep neural networks…

Supervised machine learning often operates on the data-driven paradigm, wherein internal model parameters are autonomously optimized to converge predicted outputs with the ground truth, devoid of explicitly programming rules or a priori…

Recent work has demonstrated how data-driven AI methods can leverage consumer protection by supporting the automated analysis of legal documents. However, a shortcoming of data-driven approaches is poor explainability. We posit that in this…

Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…