Options of Interest: Temporal Abstraction with Interest Functions
Posted on10/01/2020
Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of... Read More
A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry
Posted on10/12/2019
Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement... Read More
Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM
Posted on10/12/2019
Many real-world data sets, especially in biology, are produced by complex nonlinear dynamical systems. In this paper, we focus on brain calcium... Read More
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
Posted on10/12/2019
We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which learns kernelized hashcodes as... Read More
Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Posted on10/12/2019
Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective... Read More
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
Posted on10/12/2019
Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network... Read More
Contextual Bandit with Restricted Context
Posted on10/12/2019
We consider a novel formulation of the multi-armed bandit model, which we call the con-textual bandit with restricted context, where only a... Read More
Learning stable and predictive network-based patterns of schizophrenia and its clinical symptoms
Posted on10/12/2019
Schizophrenia is often associated with disrupted brain connectivity. However, identifying specific neuroimaging-based patterns pathognomonic for schizophrenia and related symptom severity remains a... Read More
Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World
Posted on10/12/2019
In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model architecture. We propose... Read More
Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
Posted on10/12/2019
One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject... Read More