Gideon Kowadlo

New approaches to Deep Networks – Capsules (Hinton), HTM (Numenta), Sparsey (Neurithmic Systems) and RCN (Vicarious)

by Gideon Kowadlo
December 1, 2017December 2, 2017
2 Comments

Reproduced left to right from [8,10,1] Within a 5 day span in October, 4 papers came out that take a significantly different approach to AI hierarchical networks. They are all inspired by biological principles to varying degrees. It’s exciting to see different ways of thinking. Particularly at a time… Read More »New approaches to Deep Networks – Capsules (Hinton), HTM (Numenta), Sparsey (Neurithmic Systems) and RCN (Vicarious)

Continuous Learning

by Gideon Kowadlo
August 28, 2017February 18, 2018

The standard machine learning approach is to learn to accomplish a specific task with an associated dataset. A model is trained using the dataset and is only able to perform that one task. This is in stark contrast to animals which continue to learn throughout life and accumulate and… Read More »Continuous Learning

AGI Experimental Framework

by Gideon Kowadlo
August 20, 2017November 20, 2017

We’re very excited to launch AGI Experimental Framework, AGIEF, our open source framework. We first introduced it a while back, at the end of 2015 here, and it has certainly come a long way. AGIEF was created to make running rigorous AI experiments convenient, reproducible and scalable. The goals are:… Read More »AGI Experimental Framework

Open Sourcing MNIST and NIST Preprocessing Code

by Gideon Kowadlo
April 28, 2017November 29, 2017

In our most recent post we discussed the current set of experiments that we are conducting, using the MNIST dataset. We’ve also been looking at the NIST dataset which is similar, but extends to handwritten letters (as well as digits). These are extremely popular datasets and freely available, so make… Read More »Open Sourcing MNIST and NIST Preprocessing Code

Intuition over reasoning for AI

by Gideon Kowadlo
February 2, 2016November 20, 2017
4 Comments

By Gideon Kowadlo I’m reading a fascinating book called The Righteous Mind, by Jonathan Haidt. It’s one of those reads that can fundamentally shift the way that you see the world. In this case, the human world, everyone around you, and yourself. A central idea of the book is that… Read More »Intuition over reasoning for AI

AGI Experimental Framework: A platform for AGI R&D

by Gideon Kowadlo
September 10, 2015November 20, 2017
2 Comments

By Gideon Kowadlo and David Rawlinson Introduction We’ve been building and testing AGI algorithms for the last few years. As the systems become more complex, we have found it ever more difficult to run meaningful experiments. To summarise, the main challenges are: testing a version of the algorithm repeatedly and… Read More »AGI Experimental Framework: A platform for AGI R&D

A nomenclature for Cortical Columns and related concepts.

by Gideon Kowadlo
May 8, 2015December 22, 2017

By Gideon Kowadlo and David Rawlinson In our last blog post, we discussed the repeating functional columnar structure of the neocortex, and the inconsistent terminology used to discuss it throughout the literature. As mentioned in that post, the function of the column is an important concept for understanding the function of the… Read More »A nomenclature for Cortical Columns and related concepts.

Mini, macro, micro and hyper columns: confusing terminology

by Gideon Kowadlo
April 27, 2015December 22, 2017

Cell-type-specific 3D reconstruction of five neighboring barrel columns in rat vibrissal cortex (credit: Marcel Oberlaender et al.) It is well established that there is a functional columnar structure repeated throughout the cortex across species (the concept received significant attention after a study by Mountcastle in 1957 [1]; see [2] and… Read More »Mini, macro, micro and hyper columns: confusing terminology

Eric Horvitz on the new era of AI

by Gideon Kowadlo
February 25, 2015November 20, 2017

I found this video interview with Eric Horvitz, the head of Microsoft Research, to be a really interesting window into their work and vision – a large part of which is AI. As Eric states, there is a “growing consensus that the next, if not last, enduring competitive battlefield, among… Read More »Eric Horvitz on the new era of AI

Mitigating the perceived future risks of AI

by Gideon Kowadlo
February 21, 2015December 22, 2017

Just a few days ago, Jay posted here about the recent public attention to AI and the potential future dangers that it presents. Discussion on the topic continues, but it’s not all talk. There are at least two institutes focussed on practical steps to mitigate the risks. There is an… Read More »Mitigating the perceived future risks of AI