Blog Posts - Project AGI

AHA! an ‘Artificial Hippocampal Algorithm’ for Episodic Machine Learning

by Gideon Kowadlo
November 12, 2019November 21, 2019
2 Comments

We’re very happy to report that we recently published a preprint on AHA, an ‘Artificial Hippocampal Algorithm’ for Episodic Machine Learning. It’s the culmination of… Read More »

Hippocampus and the Episodic confusion (for machine learning)

by Gideon Kowadlo
November 11, 2019November 21, 2019

The standard definitions of Episodic and Semantic Memory hide some important subtleties that impact the development of Machine Learning algorithms for AI (particularly those building Episodic Learning capability). This article explores this issue and provides a context for upcoming articles work to take us a step closer to 'animal-like' machine learning

Biologically-plausible learning rules for artificial neural networks

by David Rawlinson
November 11, 2019November 11, 2019

Artificial neural networks (ANNs) – are conceptually simple; the combination of inputs and weights in a classical ANN can be represented as a single matrix… Read More »

Learning partially-observable higher-order sequences using local and immediate credit assignment

by David Rawlinson
June 28, 2019

One of our key projects is a memory system that can learn to associate distant cause & effect while only using local, immediate & unsupervised… Read More »

Cerebral networks for conscious access and decision making

by Naoya Arakawa
June 8, 2019June 28, 2019

Originally published in March 2019 in an electronic journal in Japanese Introduction The purpose of this essay is to survey the relationship between decision making… Read More »

Learning distant cause and effect using only local and immediate credit assignment

by David Rawlinson
May 29, 2019

We’ve uploaded a new paper to arXiv presenting our algorithm for biologically-plausible learning of distant cause & effect using only local and immediate credit assignment.… Read More »

AI is already harming us – but not the way you think

by David Rawlinson
March 19, 2019March 20, 2019

As AI/ML researchers, we have obviously pondered the risks of AI. We even wrote about it. But what might surprise you is the risks that… Read More »

Optimization using Adam on Sparse Tensors

by Abdelrahman Ahmed
February 28, 2019March 18, 2019

Adaptive optimization methods, such as Adam and Adagrad, maintain some statistics over time about the variables and gradients (e.g. moments) which affect the learning rate.… Read More »

Predictive Capsules Networks – Research update

by David Rawlinson
November 29, 2018November 29, 2018

We recently talked about Capsules networks and equivariances. NB: If you’re not familiar with Capsules networks, read this first. Our primary objective with Capsules networks is… Read More »

New ML/Neuroscience Research Projects – ‘Self Organising Architectures’ and ‘Bicameral Brains’

by Gideon Kowadlo
October 8, 2018October 8, 2018

We recently published 2 new ML/neuroscience research projects as part of the Request for Research (RFRs) projects, with WBAI. They’re fascinating topics that have arisen through the relationship with our advisor Elkhonon Goldberg from the Luria Neuroscience Institute.