Neuroscience-Inspired Artificial Intelligence.

By Demis Hassabis, Dharshan Kumaran, Christopher Summerfield, Matthew Botvinick. 2017

1,404 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Neuroscience

How researchers see this paper

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

In Cognitive Neuroscience

In Neuroscience

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, background): “However, there is some interesting recent work connecting neuroscience and artificial neural networks, indicating an increase in the cross-fertilization between the two fields [43, 44, 45].”
Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, background): “Artificial agents interacting in dynamic environments are required to continually acquire and fine-tune their knowledge over time (Thrun and Mitchell, 1995; Hassabis et al., 2017; Parisi et al., 2018).”
Continual World: A Robotic Benchmark For Continual Reinforcement Learning (2021, background): “The progress in this area could offer enormous advantages for deep neural networks [18] and move the community closer to the long-term goal of building intelligent machines [19].”
Replay in Deep Learning: Current Approaches and Missing Biological Elements (2021, neutral): “…supervised classification, experience replay in reinforcement learning is inspired by the interplay between memory systems in the mammalian brain; its biological plausibility has been discussed in Schaul, Quan, Antonoglou, and Silver (2016) and Hassabis, Kumaran, Summerfield, and Botvinick (2017).”
GAN Memory with No Forgetting (2020, background): “Lifelong learning (or continual learning) is a long-standing challenge for machine learning and artificial intelligence systems [76, 28, 73, 11, 14, 60], concerning the ability of a model to continually learn new knowledge without forgetting previously learned experiences.”
Orthogonal Gradient Descent for Continual Learning (2019, background): “Despite their ubiquity in the real world, these problems have posed a long-standing challenge to artificial intelligence (Thrun and Mitchell, 1995; Hassabis et al., 2017).”
Continual Few-Shot Learning for Text Classification (2021, background): “ing (French, 1999; Hassabis et al., 2017), defined as an adaptive system capable of learning from a continuous stream of information.”