publications

2023

1. 

   General Sequential Episodic Memory Model

   Arjun Karuvally, Terrence J. Sejnowski, and Hava T. Siegelmann

   In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, 2023

   Abs PDF

   The state-of-the-art memory model is the General Associative Memory Model, a generalization of the classical Hopfield network. Like its ancestor, the general associative memory has a well-defined state-dependant energy surface, and its memories correlate with its fixed points. This is unlike human memories, which are commonly sequential rather than separated fixed points. In this paper, we introduce a class of General Sequential Episodic Memory Models (GSEMM) that, in the adiabatic limit, exhibit a dynamic energy surface, leading to a series of meta-stable states capable of encoding memory sequences. A multiple-timescale architecture enables the dynamic nature of the energy surface with newly introduced asymmetric synapses and signal propagation delays. We demonstrate its dense capacity under polynomial activation functions. GSEMM combines separate memories, short and long sequential episodic memories, under a unified theoretical framework, demonstrating how energy-based memory modeling can provide richer, human-like episodes.

2. 

   Episodic Memory Theory of Recurrent Neural Networks: Insights into Long-Term Information Storage and Manipulation

   Arjun Karuvally, Peter DelMastro, and Hava T. Siegelmann

   In Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) at the 40th International Conference on Machine Learning ICML 2023, 2023

   Abs PDF

   Recurrent neural networks (RNNs) have emerged as powerful models capable of storing and manipulating external information over long periods in various domains. Yet, the mechanisms that underly this behavior remain a mystery due to the black-box nature of these models. This paper addresses this question by proposing an episodic memory theory of RNN dynamics, enabling a more comprehensive understanding of the RNN weights as memories and inter-memory interactions. This approach sheds light on the inner workings of RNNs and connects to existing research on memory representation and organization. The theory extends the current linearization approaches by providing alternative interpretations of the eigenspectrum and its connection to the long-term storage and manipulation of information. We discuss how the segregation, representation, and composition of the variable binding problem—a fundamental question in cognitive science and artificial intelligence—can be mechanistically interpreted within the theory. Using an elementary task - repeat copy, we demonstrate the validity of the theory in experimental settings. Our work represents a step towards opening the black box of RNNs, offering new insights into their functionality and bridging the gap between recurrent neural networks and memory models.

2022

1. Energy-based General Sequential Episodic Memory Networks at the Adiabatic Limit

   Arjun Karuvally, Terry J. Sejnowski, and Hava T. Siegelmann

   CoRR, 2022

   arXiv

2019

1. Learning proposals for sequential importance samplers using reinforced variational inference

   Zafarali Ahmed, Arjun Karuvally, Doina Precup, and 1 more author

   In Deep Reinforcement Learning Meets Structured Prediction, ICLR 2019 Workshop, New Orleans, Louisiana, United States, May 6, 2019, 2019

   PDF

2018

1. Cache Miss Rate Predictability via Neural Networks

   Arjun Karuvally, Rishikesh Jha, Saket Tiwari, and 1 more author

   In Workshop on ML for Systems at NeurIPS 2018, 2018

   PDF