HBS

Description

Analogic / digital brain with Opamps and PICs

Details

Project Logs

Collapse logs

HBS progress 27
Robert Gonzalez • 11/16/2019 at 15:12 • 0 comments

Next test. I'm going to change all system to digital without use Opamps.
HBS progress 26
Robert Gonzalez • 11/13/2019 at 18:32 • 0 comments

error propagation like cardiogram :D.

I can't up velocity because I need wait the signal be stabilized but it is slow because is obtained from low pass filter after PWM.
If period is reduced the stabilization is more fast but I loss precision and entire period is shared between 5 PWMs too.
Noise is natural regularization :)
HBS progress 25
Robert Gonzalez • 11/11/2019 at 20:17 • 0 comments

corrections...
HBS progress 24
Robert Gonzalez • 11/09/2019 at 14:13 • 0 comments

Limiters added...
HBS progress 23
Robert Gonzalez • 11/07/2019 at 02:35 • 0 comments

modifications to limitate voltage before PIC input to avoid some undesired spikes.
HBS progress 22
Robert Gonzalez • 11/04/2019 at 19:55 • 0 comments
HBS progress 21
Robert Gonzalez • 10/30/2019 at 06:10 • 0 comments

PWM changed from 128Hz to 600Hz.

Preparing opamps and another PWM for neuron weight cost.

each weight has adjusted with ±100Mv max (output*weight).
HBS progress 20
Robert Gonzalez • 10/27/2019 at 13:46 • 0 comments

Error propagation (yellow) of output neuron after propagation and cost calculation of memorized state0 (blue when yellow HIGH). Or no error propagation (LOW yellow) when state1 (actual input) is propagated (blue when yellow LOW)

On next image reward is 0 but with max/min rewards is reached from 0 to 5v.
HBS progress 19
Robert Gonzalez • 10/27/2019 at 02:13 • 0 comments

ready cost calculation
HBS progress 18
Robert Gonzalez • 10/25/2019 at 15:39 • 0 comments

Master neuron (first neuron on input layer) doing a propagate signal to adjacent neuron (first layer only) and all first layer neuron alternates between memorized state (state0) (HIGH) or respond to actual input (state1) (LOW) in a consecutively mode.