Towards a Predictive Processing Implementation of the Common Model of Cognition

Ororbia, Alexander; Kelly, M. A.

doi:10.48550/arxiv.2105.07308

Cited by 2 publications

(2 citation statements)

References 30 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the many potential directions that merit exploration with respect to ED-FF credit assignment, we believe that investigating how the adaptation process would operate in the context of far more complex data, such as natural images (assuming that the spiking system was equipped with the proper inductive biases) and sequences, e.g., video frames, will be important. Furthermore, it would be interesting to observe how spike-level circuitry, adapted via ED-FF learning, might be useful for neural-centric cognitive architectures [51,52,57], inspired by the success of models such as the Semantic Pointer Architecture (SPAUN) [74].…”

Section: Discussionmentioning

confidence: 99%

Contrastive-Signal-Dependent Plasticity: Forward-Forward Learning of Spiking Neural Systems

Ororbia¹

2023

Preprint

View full text Add to dashboard Cite

We develop a novel credit assignment algorithm for information processing with spiking neurons without requiring feedback synapses. Specifically, we propose an event-driven generalization of the forward-forward and the predictive forward-forward learning processes for a spiking neural system that iteratively processes sensory input over a stimulus window. As a result, the recurrent circuit computes the membrane potential of each neuron in each layer as a function of local bottom-up, top-down, and lateral signals, facilitating a dynamic, layer-wise parallel form of neural computation. Unlike spiking neural coding, which relies on feedback synapses to adjust neural electrical activity, our model operates purely online and forward in time, offering a promising way to learn distributed representations of sensory data patterns with temporal spike signals. Notably, our experimental results on several pattern datasets demonstrate that the even-driven forward-forward (ED-FF) framework works well for training a dynamic recurrent spiking system capable of both classification and reconstruction.

show abstract

Section: Discussionmentioning

confidence: 99%

Contrastive-Signal-Dependent Plasticity: Forward-Forward Learning of Spiking Neural Systems

Ororbia¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Solid arrows pass data while dashed arrows modulate data passing. in form of a new cognitive architecture, CogNGen (the COGnitive Neural GENerative system; [48,51,52]). CogNGen is built on two neurobiologically and cognitively plausible models, namely a variant of predictive processing [9,64] known as neural generative coding (NGC; [54]) and vector-symbolic (a.k.a.…”

Section: Introductionmentioning

confidence: 99%

A Neuro-Mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization

Ororbia,

Kelly

2023

Preprint

View full text Add to dashboard Cite

Over the last few years, large neural generative models, capable of synthesizing intricate sequences of words or producing complex image patterns, have recently emerged as a popular representation of what has come to be known as "generative artificial intelligence'" (generative AI). Beyond opening the door to new opportunities as well as challenges for the domain of statistical machine learning, the rising popularity of generative AI brings with it interesting questions for Cognitive Science, which seeks to discover the nature of the processes that underpin minds and brains as well as to understand how such functionality might be acquired and instantiated in biological (or artificial) substrate. With this goal in mind, we argue that a promising long-term pathway lies in the crafting of cognitive architectures, a long-standing tradition of the field, cast fundamentally in terms of neuro-mimetic generative building blocks. Concretely, we discuss the COGnitive Neural GENerative system, which is an architecture that casts the Common Model of Cognition in terms of Hebbian adaptation operating in service of optimizing a variational free energy functional.

show abstract

Towards a Predictive Processing Implementation of the Common Model of Cognition

Cited by 2 publications

References 30 publications

Contrastive-Signal-Dependent Plasticity: Forward-Forward Learning of Spiking Neural Systems

Contrastive-Signal-Dependent Plasticity: Forward-Forward Learning of Spiking Neural Systems

A Neuro-Mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization

Contact Info

Product

Resources

About