6708 sinewave 2

SynthNN - Part 1: A Synthesized Neural Network

SynthNN is a fringe research project being created at The Ape Machine. It uses wave oscillation to transfer signals between neurons in a neural network.

SynthNN, or the Synthesized Neural Network, is an experiment in designing a new type of artificial intelligence being developed here at The Ape Machine.
Our project does not try to take much inspiration from the human biological model, as we are of the opinion that computers should not try to venture into areas they are not designed for, and should stay within their digital domain.

Because of this reason our ultimate goal is not to reach any form of artificial human intelligence, but to build something that outperforms human (eventually), while using approaches that fit the way the hardware is designed.

Currently, SynthNN is not functional enough to perform any of the standard machine learning party tricks, and it wouldn't even be able to solve the MNIST challenge.
We are solely focused on building out the inner workings of a single neuron in the system, continuing from there to model the way neurons will communicate with other neurons in the network.


The newsletter will keep you informed of interesting projects in the fast-growing field of A.I. and machine learning.
Of course, we promise we will not spam you, and no shameless self-promotion.

PRO TIP: Highlight any text to share a quote easily!

Oscillating Neural Networks

The main idea behind SynthNN is to have a neural network running in real-time, while feeding forward its value to connected neurons. Each neuron in the network with multiple inputs will base its current value on the sum of the incoming waveforms. This will result in constructive and destructive interference.


On the left you can see a simple example of three neurons, x and y feed into z, the last one being the sum of the previous two.

The idea behind this is to experiment with a more fluid way of having floating point values interact with each other, and to try and avoid any type of backward propagation and gradient descent.
Using the oscillating values frequencies and amplitudes can be increased, and phase can be off-set to create a system that can be balanced.
Currently we use a very simple approach to balancing neurons, by just syncing the waveforms of neurons that tend to fire together to make their impact greater on the neurons down the line.

This effectively implements a rudimentary form of reinforcement learning.

Machine learning get started

HOWTO: Get Started With Machine Learning! (4 Tips)

So you want to know more about machine learning, and how to get started?
Maybe you want to get into the field of technical artificial intelligence, or learn more about the current state of A.I. philosophy.

In this post I will give you some invaluable pointers to resources you can use today to get a better grip on this new and exciting field of research that is taking the world by storm.

Whether you are a programmer, data scientist, mathematician, or in any other way interested in machine learning, there should be something in here for all of you.

Regulating artificial intelligence

Regulating A.I. (part 1): Origins

Elon Musk is really doubling down on the idea of introducing regulation in the field of artificial intelligence and machine learning.

This all started during the National Governors Association back in July 2017.
Nevada Rupublican Governor Brian Sandovall asked Elon Musk if robots will take everyone’s jobs in the future and Musk answers went far beyond the question asked.

Besides saying that “robots will do everything better than us,” his worries extended into the realm of what is currently still all based in nothing but science fiction.

Facebook ai new language

Facebook's A.I. Did Not Invent A New Language

So, Facebook researchers have taken their machine learning algorithm offline, which as far as I can tell was being used as an experimental chatbot program.
Of course most of the media is jumping on this story with the usual sensationalism, and are quick to connect this to the remarks made by Elon Musk, and Mark Zuckerberg, trying desparately to use this as fodder to determine which one was right, and which one was wrong.
The answer to that last part, by the way, is: Both, and neither.