EOgmaNeo vs. RNN: Simple Sequence Task

Hello! While working on some more bombastic demos, we decided to do a straight-up comparison between LSTM/GRU based recurrent neural networks and our fast online learning library, EOgmaNeo. We will compare RNNs and EOgmaNeo on a simple sequence task: Sequence copying. I know, I know, lame! But, (perhaps selfishly) I think the results are interesting…

Source Code for “Self Driving Car Learns Online and On-board on Raspberry Pi 3”

Hello! In the previous post, we demonstrated a self-driving model car that performed all processing on-board on a Raspberry Pi 3. We have now released the code for the car and associated tools. The following repositories are available on GitHub: EOgmaNeo – the primary library containing our super-fast online learning technology! EOgmaDrive – a description…

Exponential Memory

Hello! We have been working hard on the latest version of OgmaNeo, and in the latest version (v1.3) introduced something we call “Exponential Memory”. We believe this to be an important step forward that applies not only to what we have in OgmaNeo already, but also to Deep Learning in general. In simplest terms, Exponential…

OgmaNeo Ball Physics Simulation

The following is a rundown of a new demo added to the OgmaNeoDemos¬†repository, Ball Physics Prediction. We plan to release new demos regularly! Ball Physics Prediction/Simulation An important aspect of world modeling in humans is the ability to simulate physical interactions ahead of time. Let’s try to make a simple demo of this using OgmaNeo!…

OgmaNeo Overview and Video Prediction

Here is an overview of the Feynman Machine architecture used in the OgmaNeo library, followed by an example for video prediction (recall). For the original Feynman Machine paper, see¬†https://arxiv.org/abs/1609.03971. A High Level Look at the Feynman Machine The Feynman Machine is a hierarchical sequence prediction algorithm that functions on the basis of coupled dynamical systems.…