102 citations · 251 across the 20 of their papers we have counts for
20 papers
Neither hype nor gloom do DNNs justice
Felix A. Wichmann, Simon Kornblith, Robert Geirhos
Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNN…
Fixing the problems of deep neural networks will require better training data and learning algorithms
Drew Linsley, Thomas Serre
Bowers and colleagues argue that DNNs are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those…
Synaptic Weight Distributions Depend on the Geometry of Plasticity
Roman Pogodin, Jonathan Cornford, Arna Ghosh +3
A growing literature in computational neuroscience leverages gradient descent and learning algorithms that approximate it to study synaptic plasticity in the brain. However, the va…
Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics
Conor Houghton, Nina Kazanina, Priyanka Sukumaran
Large language models are not detailed models of human linguistic processing. They are, however, extremely successful at their primary task: providing a model for language. For thi…
Transfer Entropy Bottleneck: Learning Sequence to Sequence Information Transfer
Damjan Kalajdzievski, Ximeng Mao, Pascal Fortier-Poisson +2
When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream) can benefit from information about bot…
Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution
Anthony Zador, Sean Escola, Blake Richards +24
Neuroscience has long been an essential driver of progress in artificial intelligence (AI). We propose that to accelerate progress in AI, we must invest in fundamental research in…
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
Chen Sun, Wannan Yang, Thomas Jiralerspong +4
In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward. These critical steps are challenging to i…
The neuroconnectionist research programme
Adrien Doerig, Rowan Sommers, Katja Seeliger +8
Artificial Neural Networks (ANNs) inspired by biology are beginning to be widely used to model behavioral and neural data, an approach we call neuroconnectionism. ANNs have been la…
On Neural Architecture Inductive Biases for Relational Tasks
Giancarlo Kerg, Sarthak Mittal, David Rolnick +3
Current deep learning approaches have shown good in-distribution generalization performance, but struggle with out-of-distribution generalization. This is especially true in the ca…
Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules
Yuhan Helena Liu, Arna Ghosh, Blake A. Richards +2
To unveil how the brain learns, ongoing work seeks biologically-plausible approximations of gradient descent algorithms for training recurrent neural networks (RNNs). Yet, beyond t…
Evaluating Multimodal Interactive Agents
Josh Abramson, Arun Ahuja, Federico Carnevale +12
Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research. However, evaluating these interactions is challenging: collecting…
Investigating Power laws in Deep Representation Learning
Arna Ghosh, Arnab Kumar Mondal, Kumar Krishna Agrawal +1
Representation learning that leverages large-scale labelled datasets, is central to recent progress in machine learning. Access to task relevant labels at scale is often scarce or…
Towards Scaling Difference Target Propagation by Learning Backprop Targets
Maxence Ernoult, Fabrice Normandin, Abhinav Moudgil +5
The development of biologically-plausible learning algorithms is important for understanding learning in the brain, but most of them fail to scale-up to real-world tasks, limiting…
A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions
Anthony GX-Chen, Veronica Chelu, Blake A. Richards +1
Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootstrapping, i.e. they update the value func…
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Nicholas Roy, Ingmar Posner, Tim Barfoot +17
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains. Consequently, the notion of applying learning metho…
Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece
Luke Y. Prince, Roy Henha Eyono, Ellen Boven +9
We provide a brief review of the common assumptions about biological learning with findings from experimental neuroscience and contrast them with the efficiency of gradient-based l…
Adversarial Feature Desensitization
Pouya Bashivan, Reza Bayat, Adam Ibrahim +5
Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can drastically impair the network's perform…
Spike-based causal inference for weight alignment
Jordan Guerguiev, Konrad P. Kording, Blake A. Richards
In artificial neural networks trained with gradient descent, the weights used for processing stimuli are also used during backward passes to calculate gradients. For the real brain…
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
Sergey Bartunov, Adam Santoro, Blake A. Richards +3
The backpropagation of error algorithm (BP) is impossible to implement in a real brain. The recent success of deep networks in machine learning and AI, however, has inspired propos…
Towards deep learning with segregated dendrites
Jordan Guergiuev, Timothy P. Lillicrap, Blake A. Richards
Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning…