What can the brain teach us about building artificial intelligence?

By Brenden M. Lake, Tomer D. Ullman, Josh Tenenbaum, Samuel J. Gershman. 2016

848 citations recorded by the source corpus.

Abstract Lake et al. offer a timely critique on the recent accomplishments in artificial intelligence from the vantage point of human intelligence and provide insightful suggestions about research directions for building more human-like intelligence. Because we agree with most of the points they raised, here we offer a few points that are complementary.

Subfields: Cognitive Neuroscience, Experimental and Cognitive Psychology, Neuroscience, Cognitive Science & Psychology

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 Experimental and Cognitive Psychology

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

Learning Transferable Visual Models From Natural Language Supervision (2021, background): “This suggests that there are still algorithmic improvements waiting to be made to decrease the gap between machine and human sample efficiency, as noted by Lake et al. (2016) and others.”
Shortcut learning in deep neural networks (2020, background): “We, among many others [93, 78, 94, 95, 96], have explored a variety of o.”
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation (2020, background): “A recent line of work has argued that representations that are disentangled are an important step towards a better representation learning (Bengio et al., 2013; Peters et al., 2017; LeCun et al., 2015; Bengio et al., 2007; Schmidhuber, 1992; Lake et al., 2017; Tschannen et al., 2018).”
Benchmark and Survey of Automated Machine Learning Frameworks (2019, background): “Self-play (Lake et al., 2017) is a reinforcement learning strategy that has received a lot of attention lately due to the recent successes of AlphaZero (Silver et al., 2017).”
Survey on Automated Machine Learning (2019, background): “Self-play (Lake et al., 2017) is a reinforcement learning strategy that has received a lot of attention lately due to the recent successes of AlphaZero (Silver et al., 2017).”
Meta-SGD: Learning to Learn Quickly for Few Shot Learning (2017, background): “ata efﬁciency and fast adaptation, if realized in machine learning, can greatly expand its utility. This motivates the study of few-shot learning, which aims to learn quickly from only a few examples [15]. Several existing ideas may be adapted for few-shot learning. In transfer learning, one often ﬁ”
On the Binding Problem in Artificial Neural Networks (2020, methodology): “Closely related to the mental framework proposed here is that of Lake et al. (2017), which is similarly concerned with addressing human-level generalization.”
Invariant Risk Minimization (2019, background): “Understanding which patterns are useful has been previously studied as a correlation-versus-causation dilemma, since spurious correlations stemming from data biases are unrelated to the causal explanation of interest [31, 27, 35, 52].”
On the Fairness of Disentangled Representations (2019, background): “Indeed, isolating each independent factor of variation into the independent components of a representation vector should make it both interpretable and simplify downstream prediction tasks [6, 7, 29, 35, 56, 58, 60, 74, 82, 87, 89, 90, 1, 28].”
Reinforcement Learning in Healthcare: A Survey (2019, methodology): “be applying various model modification or domain adaptation methods such as knowledge distillation [347] or meta-learning [348] to enable efficient learning that overcomes the problem of data scarcity.”
Unmasking Clever Hans predictors and assessing what machines really learn (2019, background): “Although learning machines have become increasingly successful, they often behave very differently from humans [37, 38].”
Relational Deep Reinforcement Learning (2018, background): “Unfortunately, deep RL models still face important limitations, namely, low sample efficiency and a propensity not to generalize to seemingly minor changes in the task [4, 5, 6, 7].”
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation (2016, background): “There is converging evidence in developmental psychology that human infants, primates, children, and adults in diverse cultures base their core knowledge on certain cognitive systems including – entities, agents and their actions, numerical quantities, space, social-structures and intuitive theories”
Learning to Act by Predicting the Future (2016, background): “Another is the acquisition of general skills that can be flexibly deployed to accomplish a multitude of dynamically specified goals (Lake et al., 2016).”
Machine Theory of Mind (2018, background): “Rather, we focus on the problem of how an observer could learn autonomously how to model other agents using limited data (Botvinick et al., 2017).”
Active Long Term Memory Networks (2016, background): “The recent interest in bridging human and machine computations [5, 6, 7, 8] obliges to consider a learning framework that is continual, sequential in nature and potentially lifelong [9, 10].”
Taskonomy: Disentangling Task Transfer Learning (2018, background): “compositional modeling [33, 8, 11, 21, 53, 89, 87], homomorphic cryptography [40], lifelong learning [90, 13, 82, 81], functional maps [68], certain aspects of Bayesian inference and Dirichlet processes [52, 88, 87, 86, 35, 37], few-shot learning [78, 23, 22, 67, 83], transfer learning [72, 81, 27, ”
Model-Free Episodic Control (2016, background): “As pointed out by [13], humans learn to play these games much faster.”
Auto-Encoding Scene Graphs for Image Captioning (2018, background): “language can be considered as the inductive bias that is apprehended by us from everyday practice, which makes us performing better than machines in high-level reasoning [22, 5].”