Related papers: Avalanche: an End-to-End Library for Continual Lea…

This paper presents a comprehensive comparative survey of TensorFlow and PyTorch, the two leading deep learning frameworks, focusing on their usability, performance, and deployment trade-offs. We review each framework's programming paradigm…

Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-specific properties. We…

We design and implement a ready-to-use library in PyTorch for performing micro-batch pipeline parallelism with checkpointing proposed by GPipe (Huang et al., 2019). In particular, we develop a set of design components to enable…

Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well…

Continual learning is an emerging subject in machine learning that aims to solve multiple tasks presented sequentially to the learner without forgetting previously learned tasks. Recently, many deep learning based approaches have been…

Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused…

We propose an approach for anytime continual learning (AnytimeCL) for open vocabulary image classification. The AnytimeCL problem aims to break away from batch training and rigid models by requiring that a system can predict any set of…

We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming. The torchbearer library provides a high level metric and callback API that can be used for a wide…

Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning…

We release a new Bayesian neural network library for PyTorch for large-scale deep networks. Our library implements mainstream approximate Bayesian inference algorithms: variational inference, MC-dropout, stochastic-gradient MCMC, and…

This paper introduces EvoCraft, a framework for Minecraft designed to study open-ended algorithms. We introduce an API that provides an open-source Python interface for communicating with Minecraft to place and track blocks. In contrast to…

Continual learning is the problem of learning and retaining knowledge through time over multiple tasks and environments. Research has primarily focused on the incremental classification setting, where new tasks/classes are added at discrete…

Continual learning is an online paradigm where a learner continually accumulates knowledge from different tasks encountered over sequential time steps. Importantly, the learner is required to extend and update its knowledge without…

Despite the vast body of literature on Active Learning (AL), there is no comprehensive and open benchmark allowing for efficient and simple comparison of proposed samplers. Additionally, the variability in experimental settings across the…

advertorch is a toolbox for adversarial robustness research. It contains various implementations for attacks, defenses and robust training methods. advertorch is built on PyTorch (Paszke et al., 2017), and leverages the advantages of the…

We present PyTorch Geometric Temporal a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing. The main goal of the library is to make temporal geometric deep learning…

The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning…

Recurrent neural networks (RNNs) are a cornerstone of sequence modeling across various scientific and industrial applications. Owing to their versatility, numerous RNN variants have been proposed over the past decade, aiming to improve the…

Peer-to-peer (P2P) overlay networks such as BitTorrent and Avalanche are increasingly used for disseminating potentially large files from a server to many end users via the Internet. The key idea is to divide the file into many…

YAMLE: Yet Another Machine Learning Environment is an open-source framework that facilitates rapid prototyping and experimentation with machine learning (ML) models and methods. The key motivation is to reduce repetitive work when…