Deep learning for AI

By Yoshua Bengio, Yann LeCun, Geoffrey E. Hinton. 2021

645 citations recorded by the source corpus.

How can neural networks learn the rich internal representations required for difficult tasks such as recognizing objects or understanding language?

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Large Language Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Large Language Models

Citations in the corpus

Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, background): “MWP solving is typically regarded as one of the system 2 tasks (Kahneman, 2011; Bengio et al., 2021), and our current approach to this problem is related to neural symbolic reasoning (Besold et al., 2017).”
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning (2022, background): “It is also one of the most valued strengths of classical, symbolic AI over contemporary deep learning methods (Marcus & Davis, 2019; Marcus, 2020; Bengio et al., 2021), prompting the recent increase in the use of neurosymbolic approaches to bridge this gap (Garnelo & Shanahan, 2019; Garcez & Lamb, 2”
Neural Unsupervised Domain Adaptation in NLP—A Survey (2020, background): “This is the broader need for out-of-distribution generalization (Bengio, 2019), and a more challenging setup targeted at handling unknown domains (Volpi et al.”
Survey on Deep Neural Networks in Speech and Vision Systems (2019, background): “Baidu is also one of the pioneering research groups to introduce deep learning-based self-driving cars with BMW. Nvidia has invested efforts in developing state-of-the-art GPUs to support more efficient and real-time implementation of complex deep learning models [160].”
Deep Long-Tailed Learning: A Survey (2021, background): “The key enablers of deep learning are the availability of large-scale datasets, the emergence of GPUs, and the advancement of deep network architectures [9].”
OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping (2022, background): “Since the advent of deep learning [2], a great deal of effort has been devoted to developing benchmark datasets for”
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective (2023, background): “While previous efforts have evaluated various aspects of ChatGPT in law [10], ethics [41], education [22], and reasoning [3], we focus on its robustness [4], which, to our best knowledge, has not been thoroughly evaluated yet.”
PIP: Physical Interaction Prediction via Mental Imagery with Span Selection (2021, background): “*These authors contributed equally to this work With the rapid advancements in computer vision, deep learning and embodied AI [6, 7, 8], there is an increase in intuitive physics models that aim to predict physical interaction outcomes.”
Explainable AI Methods - A Brief Overview (2020, background): “Machine learning (ML) and particularly the success of “deep learning” in the last decade made AI extremely popular again [15], [25], [90].”
Membership Inference Attacks on Machine Learning: A Survey (2021, background): “Besides the powerful computational resources, the availability of large datasets is another key factor contributing to the success of ML [9].”
A Systematic Literature Review of Student’ Performance Prediction Using Machine Learning Techniques (2021, background): “According to Dr. Yoshua Bengio [3] at the University of Monreal, “research using Machine Learning (ML) is part of Artiﬁcial Intelligence (AI), seeking to provide knowledge to computers through data, observations, and close interaction with the world.”