5 papers
Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training
Deven Mahesh Mistry, Anooshka Bajaj, Yash Aggarwal +2
We investigate in-context temporal biases in attention heads and transformer outputs. Using cognitive science methodologies, we analyze attention scores and outputs of the GPT-2 mo…
Deep reinforcement learning with time-scale invariant memory
Md Rysul Kabir, James Mochizuki-Freeman, Zoran Tiganj
The ability to estimate temporal relationships is critical for both animals and artificial agents. Cognitive science and neuroscience provide remarkable insights into behavioral an…
DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales
Brandon Jacques, Zoran Tiganj, Marc W. Howard +1
Extracting temporal relationships over a range of scales is a hallmark of human perception and cognition -- and thus it is a critical feature of machine learning applied to real-wo…
Evidence accumulation in a Laplace domain decision space
Marc W. Howard, Andre Luzardo, Zoran Tiganj
Evidence accumulation models of simple decision-making have long assumed that the brain estimates a scalar decision variable corresponding to the log-likelihood ratio of the two al…
Estimating scale-invariant future in continuous time
Zoran Tiganj, Samuel J. Gershman, Per B. Sederberg +1
Natural learners must compute an estimate of future outcomes that follow from a stimulus in continuous time. Widely used reinforcement learning algorithms discretize continuous tim…