Search Results for author:
Found 39 papers, 15 papers with code
A Review of Neuroscience-Inspired Machine Learning
As a result, it accommodates hardware and scientific modeling, e. g. learning with physical systems and non-differentiable behavior.
Associative Memories in the Feature Space
This problem can be easily solved by computing \emph{similarities} in an embedding space instead of the pixel space.
BlackMamba: Mixture of Experts for State-Space Models
In this paper, we present BlackMamba, a novel architecture that combines the Mamba SSM with MoE to obtain the benefits of both.
Causal Inference via Predictive Coding
Bayesian inference models observations: what can be inferred about y if we observe a related variable x?
Designing Ecosystems of Intelligence from First Principles
In this context, we understand intelligence as the capacity to accumulate evidence for a generative model of one's sensed world -- also known as self-evidencing.
Interpreting Neural Networks through the Polytope Lens
Previous mechanistic descriptions have used individual neurons or their linear combinations to understand the representations a network has learned.
A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience.
Predictive Coding beyond Gaussian Distributions
A large amount of recent research has the far-reaching goal of finding training methods for deep neural networks that can serve as alternatives to backpropagation (BP).
Capsule Networks as Generative Models
Capsule networks are a neural network architecture specialized for visual scene recognition.
Preventing Deterioration of Classification Accuracy in Predictive Coding Networks
Predictive Coding Networks (PCNs) aim to learn a generative model of the world.
A Theoretical Framework for Inference and Learning in Predictive Coding Networks
In this paper, we provide a comprehensive theoretical analysis of the properties of PCNs trained with prospective configuration.
Successor Representation Active Inference
Recent work has uncovered close links between between classical reinforcement learning algorithms, Bayesian filtering, and Active Inference which lets us understand value functions in terms of Bayesian posteriors.
A Theoretical Framework for Inference Learning
Our novel implementation considerably improves the stability of IL across learning rates, which is consistent with our theory, as a key property of implicit SGD is its stability.
Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning
How the brain performs credit assignment is a fundamental unsolved problem in neuroscience.
Hybrid Predictive Coding: Inferring, Fast and Slow
This is at odds with evidence that several aspects of visual perception - including complex forms of object recognition - arise from an initial "feedforward sweep" that occurs on fast timescales which preclude substantial recurrent activity.
Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?
The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning.
Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models
A large number of neural network models of associative memory have been proposed in the literature.
Learning on Arbitrary Graph Topologies via Predictive Coding
Training with backpropagation (BP) in standard deep learning consists of two main steps: a forward pass that maps a data point to its prediction, and a backward pass that propagates the error of this prediction back through the network.
pymdp: A Python library for active inference in discrete state spaces
Active inference is an account of cognition and behavior in complex systems which brings together action, perception, and learning under the theoretical mantle of Bayesian inference.
Active Inference in Robotics and Artificial Agents: Survey and Challenges
Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning.
Habitual and Reflective Control in Hierarchical Predictive Coding
In cognitive science, behaviour is often separated into two types.
A Mathematical Walkthrough and Discussion of the Free Energy Principle
The Free-Energy-Principle (FEP) is an influential and controversial theory which postulates a deep and powerful connection between the stochastic thermodynamics of self-organization and learning through variational inference.
Predictive Coding: a Theoretical and Experimental Review
Predictive coding offers a potentially unifying account of cortical function -- postulating that the core function of the brain is to minimize prediction errors with respect to a generative model of the world.
Applications of the Free Energy Principle to Machine Learning and Neuroscience
Firstly, we focus on predictive coding, a neurobiologically plausible process theory derived from the free energy principle which argues that the primary function of the brain is to minimize prediction errors, showing how predictive coding can be scaled up and extended to be more biologically plausible, and elucidating its close links with other methods such as Kalman Filtering.
Online reinforcement learning with sparse rewards through an active inference capsule
Our model is capable of solving sparse-reward problems with a very high sample efficiency due to its objective function, which encourages directed exploration of uncertain states.
Towards a Mathematical Theory of Abstraction
We provide a precise characterisation of what an abstraction is and, perhaps more importantly, suggest how abstractions can be learnt directly from data both for static datasets and for dynamical systems.
How particular is the physics of the free energy principle?
We discover that two requirements of the FEP -- the Markov blanket condition (i. e. a statistical boundary precluding direct coupling between internal and external states) and stringent restrictions on its solenoidal flows (i. e. tendencies driving a system out of equilibrium) -- are only valid for a very narrow space of parameters.
Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control
We propose a dichotomy in the objective functions underlying adaptive behaviour between \emph{evidence} objectives, which correspond to well-known reward or utility maximizing objectives in the literature, and \emph{divergence} objectives which instead seek to minimize the divergence between the agent's expected and desired futures, and argue that this new class of divergence objectives could form the mathematical foundation for a much richer understanding of the exploratory components of adaptive and intelligent action, beyond simply greedy utility maximization.
Neural Kalman Filtering
The Kalman filter is a fundamental filtering algorithm that fuses noisy sensory data, a previous state estimate, and a dynamics model to produce a principled estimate of the current state.
Investigating the Scalability and Biological Plausibility of the Activation Relaxation Algorithm
The recently proposed Activation Relaxation (AR) algorithm provides a simple and robust approach for approximating the backpropagation of error algorithm using only local learning rules.
Relaxing the Constraints on Predictive Coding Models
Predictive coding is an influential theory of cortical function which posits that the principal computation the brain performs, which underlies both perception and learning, is the minimization of prediction errors.
Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain
The backpropagation of error algorithm (backprop) has been instrumental in the recent success of deep learning.
Control as Hybrid Inference
The field of reinforcement learning can be split into model-based and model-free methods.
On the Relationship Between Active Inference and Control as Inference
Active Inference (AIF) is an emerging framework in the brain sciences which suggests that biological agents act to minimise a variational bound on model evidence.
Reinforcement Learning as Iterative and Amortised Inference
There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and online or offline.
Predictive Coding Approximates Backprop along Arbitrary Computation Graphs
Recently, it has been shown that backprop in multilayer-perceptrons (MLPs) can be approximated using predictive coding, a biologically-plausible process theory of cortical computation which relies only on local and Hebbian updates.
Whence the Expected Free Energy?
The Expected Free Energy (EFE) is a central quantity in the theory of active inference.
Reinforcement Learning through Active Inference
The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards.
Deep Active Inference as Variational Policy Gradients
Active Inference is a theory of action arising from neuroscience which casts action and planning as a bayesian inference problem to be solved by minimizing a single quantity - the variational free energy.
