Related papers: Predictive information in a sensory population
Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from learning systems' inability to represent all kinds of behaviors.…
We present a computational and theoretical model of the neural mechanisms underlying human decision-making. We propose a detailed model of the interaction between brain regions, under a proposer-predictor-actor-critic framework.…
Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distribution densely. We study a common setting where our task is not…
User performance is crucial in interactive systems, capturing how effectively users engage with task execution. Prospectively predicting performance enables the timely identification of users struggling with task demands. While ocular and…
In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual…
Predictive coding (PC) is an influential computational model of visual learning and inference in the brain. Classical PC was proposed as a top-down generative model, where the brain actively predicts upcoming visual inputs, and inference…
Sensory observations about the world are invariably ambiguous. Inference about the world's latent variables is thus an important computation for the brain. However, computational constraints limit the performance of these computations.…
There has been great progress in understanding of anatomical and functional microcircuitry of the primate cortex. However, the fundamental principles of cortical computation - the principles that allow the visual cortex to bind retinal…
Observations on the past provide some hints about what will happen in the future, and this can be quantified using information theory. The ``predictive information'' defined in this way has connections to measures of complexity that have…
Predictive coding is a unifying framework for understanding perception, action and neocortical organization. In predictive coding, different areas of the neocortex implement a hierarchical generative model of the world that is learned from…
Understanding neurocognitive computations will require not just localizing cognitive information distributed throughout the brain but also determining how that information got there. We review recent advances in linking empirical and…
Interactive simulations allow students to discover the underlying principles of a scientific phenomenon through their own exploration. Unfortunately, students often struggle to learn effectively in these environments. Classifying students'…
A substantial amount of time and energy has been invested to develop machine vision using connectionist (neural network) principles. Most of that work has been inspired by theories advanced by neuroscientists and behaviorists for how…
Bias in perceptual decisions comes to pass when the advance knowledge colludes with the current sensory evidence in support of the final choice. The literature on decision making suggests two main hypotheses to account for this kind of…
The current dominant visual processing paradigm in both human and machine research is the feedforward, layered hierarchy of neural-like processing elements. Within this paradigm, visual saliency is seen by many to have a specific role,…
Deep convolutional neural networks (CNNs) have demonstrated impressive performance on many visual tasks. Recently, they became useful models for the visual system in neuroscience. However, it is still not clear what are learned by CNNs in…
Theoretical models of populations and swarms typically start with the assumption that the motion of agents is governed by the local stimuli. However, an intelligent agent, with some understanding of the laws that govern its habitat, can…
Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…
Computer input is more complex than a sequence of single mouse clicks and keyboard presses. We introduce a novel method to identify and represent the user interactions and build a system which predicts - in real-time - the action a user is…
Active inference is a normative framework for explaining behaviour under the free energy principle -- a theory of self-organisation originating in neuroscience. It specifies neuronal dynamics for state-estimation in terms of a descent on…