Research

Collaboration Requests

If you’re interested in collaborating, email me at rylanschaeffer@gmail.com. I’ve posted a (work-in-progress) summary of my research approach.

Publications

In Preparation

• Schaeffer, et al. Are Emergent Abilities of Large Language Models a Mirage? 2023.

• Schaeffer *, Khona *, Fiete. Self-Supervised Learning of Efficient Algebraic Codes Generates Grid Cells. 2023.

Preprint

• Schaeffer, et al. An Introductory Tutorial on Double Descent: What Double Descent Is and Why It Occurs. 2023.

Under Review

• Bricken, Schaeffer, Olshausen, Kreiman. Emergence of Sparse Representations from Noise. ICML 2023.

Accepted

• Schaeffer, Khona, Fiete. No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit. NeurIPS 2022.

• Schaeffer, Liu, Du, Linderman, Fiete. Streaming Inference for Infinite Non-Stationary Clustering. CoLLAs 2022.

• Schaeffer, Du, Liu, Fiete. Streaming Inference for Infinite Latent Feature Models. ICML 2022.

• Schaeffer, Khona, Fiete. No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit. ICML 2022 Workshop: AI for Science.

• Schaeffer, Liu, Du, Linderman, Fiete. Streaming Inference for Infinite Non-Stationary Clustering. ICLR 2022 Workshop: Agent Learning in Open Endedness.

• Schaeffer. An Algorithmic Theory of Metacognition in Minds and Machines. NeurIPS 2021 Workshop: Metacognition in the Age of AI.

• Schaeffer, et al. Fiete, IBL. Neural population dynamics for hierarchical inference in mice performing the International Brain Lab task. Society for Neuroscience 2021.

• Schaeffer, Bordelon, Khona, Pan, Fiete. Efficient Online Inference for Nonparametric Mixture Models. UAI 2021.

• Schaeffer, Shaham, Kreiman, Sompolinsky. Neural network model of amygdalar memory engram formation and function. COSYNE 2021.

• Schaeffer, Khona, Meshulam, IBL, Fiete. Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice. NeurIPS 2020.

In Progress

• Liu, Schaeffer et al. Brain-wide population codes for hierarchical inference in mice. 2023.

Rejected

• Schaeffer et al. Streaming Inference for Infinite Latent Feature Models. AISTATS 2021.

• Schaeffer et al. Efficient Streaming Inference for Infinite Latent Feature Models. ICML 2021 Workshop on Theory and Foundation of Continual Learning.
  • Paper
• Schaeffer et al. Mechanistic neural circuit models of hierarchical inference. COSYNE 2021.
  • 2-Page Abstract

One Day

• Schaeffer et al. Memory Engrams Perform Nonparametric Latent State Associative Learning. 2022.

• Schaeffer et al. Recovering low dimensional, interpretable mechanistic models via Representations and Dynamics Distillation. 2021.

Abandoned

• Schaeffer et al. Towards Unifying Smooth Neural Codes with Adversarially Robust Representations. 2019.
  • Paper

Explanations of Others’ Research

• Neural Turing Machines
• One-shot Learning with Memory-Augmented Neural Networks
• Neural Episodic Control
• Elastic Weight Consolidation
• Early Visual Concept Learning with Unsupervised Deep Learning