2 citations · 5 across the 12 of their papers we have counts for
15 papers
Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
John J. Vastola, Ann Huang, Satpreet H. Singh +2
While animals and people tend to learn a task more quickly and reliably when they first train on simpler versions of it, curriculum learning's effectiveness in artificial settings…
CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition
Lance Ying, Jinzhou Wu, Yingshan Susan Wang +53
Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increasingly capable, in what ways…
Subjective functions
Samuel J. Gershman
Where do objective functions come from? How do we select what goals to pursue? Human intelligence is adept at synthesizing new objective functions on the fly. How does this work, a…
A Variational Manifold Embedding Framework for Nonlinear Dimensionality Reduction
John J. Vastola, Samuel J. Gershman, Kanaka Rajan
Dimensionality reduction algorithms like principal component analysis (PCA) are workhorses of machine learning and neuroscience, but each has well-known limitations. Variants of PC…
Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
John J. Vastola, Samuel J. Gershman, Kanaka Rajan
Learning rules -- prescriptions for updating model parameters to improve performance -- are typically assumed rather than derived. Why do some learning rules work better than other…
A circuit for predicting hierarchical structure in-context in Large Language Models
Tankred Saanum, Can Demircan, Samuel J. Gershman +1
Large Language Models (LLMs) excel at in-context learning, the ability to use information provided as context to improve prediction of future tokens. Induction heads have been argu…
Fast weight programming and linear transformers: from machine learning to neurobiology
Kazuki Irie, Samuel J. Gershman
Recent advances in artificial neural networks for machine learning, and language modeling in particular, have established a family of recurrent neural network (RNN) architectures t…
Assessing Adaptive World Models in Machines with Novel Games
Lance Ying, Katherine M. Collins, Prafull Sharma +11
Human intelligence exhibits a remarkable capacity for rapid adaptation and effective problem-solving in novel and unfamiliar contexts. We argue that this profound adaptability is f…
Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines
Wilka Carvalho, Sam Hall-McMaster, Honglak Lee +1
Humans can pursue a near-infinite variety of tasks, but typically can only pursue a small number at the same time. We hypothesize that humans leverage experience on one task to pre…
Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
Kazuki Irie, Morris Yau, Samuel J. Gershman
We develop hybrid memory architectures for general-purpose sequence processing neural networks, that combine key-value memory using softmax attention (KV-memory) with fast weight m…
Key-value memory in the brain
Samuel J. Gershman, Ila Fiete, Kazuki Irie
Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored pat…
Synthesizing world models for bilevel planning
Zergham Ahmed, Joshua B. Tenenbaum, Christopher J. Bates +1
Modern reinforcement learning (RL) systems have demonstrated remarkable capabilities in complex environments, such as video games. However, they still fall short of achieving human…
General Intelligence Requires Reward-based Pretraining
Seungwook Han, Jyothish Pari, Samuel J. Gershman +1
Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and rob…
How should the advent of large language models affect the practice of science?
Marcel Binz, Stephan Alaniz, Adina Roskies +15
Large language models (LLMs) are being increasingly incorporated into scientific workflows. However, we have yet to fully grasp the implications of this integration. How should the…
Grokking as the Transition from Lazy to Rich Training Dynamics
Tanishq Kumar, Blake Bordelon, Samuel J. Gershman +1
We propose that the grokking phenomenon, where the train loss of a neural network decreases much earlier than its test loss, can arise due to a neural network transitioning from la…