Close
0%
0%

NSCE-ngbrain

scalable hardware for neural network system

Similar projects worth following
scalable hardware for neural network system

  • little UI organization

    3drobert01/08/2022 at 15:29 0 comments

  • GPU fuzzy logic + GPU combinational logic :D

    3drobert01/07/2022 at 04:22 0 comments

  • NSCE UI changes

    3drobert01/06/2022 at 04:15 0 comments

    UI changes to do inference using TCP data || backprop to specific network.
    And force layout... the most crucial parameter

  • multiple ngbrain & ngbrain_ngrel connections

    3drobert01/05/2022 at 22:25 0 comments

    already I had allowing ngrel_ngrel connections. Now I'm allowing with the combinational system to have ngbrain_ngbrain ngbrain_ngrel ngrel_ngbrain connections too.

    I will be able to simulate a RISC-V with perceptron on the ALU :D

  • last codes

    3drobert01/03/2022 at 04:15 0 comments

    Still adding enhancements like:

    adadelta,

    minibatch (6CPU_iterationsx5GPU experiences),

    visualization, corrections, etc...

    Also I'm using temporal_window variable which is used on input layer to add the lastInputs+lastActions (ConvnetJS :) ), to get now a better estimates in the reinforcement learning T value.

    before:

    _N = 0
    maxval = forward(state_N+1)
    t = reward_N*maxval
    forward(state_N)
    backward(action_N, t)

     state1_t0(+1) = 1 // state0action0 usefull

     state2_t0(-1) = -1 // state1action1 usefull

    and now...:

    _N = 0
    foreach temporal_windows:
      maxval = forward(state_N+1)
      t += reward_N*maxval
      _N++
    _N = 0
    forward(state_N)
    backward(action_N, t)

    state1_t0(+1) + state2_t1(-1) = 0 // state0action0 not usefull (or take as -1?)

    state2_t0(-1) + state3_t1(+1) = 0 // state1action1 not usefull

    other example:

    state1_t0(+1) + state2_t1(+1) = 2 // state0action0 very usefull

    state2_t0(-1) + state3_t1(-1) = -2 // state1action1 very usefull

    --------------------------------------------------------------------------------------

    I want try some day what happens if I connect a blank neural network used as reward applicator (to avoid indicate any reward) and this reward net came from some type of long memory net.

    Reward net actualization will be modelated according to something like a "neurons cell energy" variables with thresholds values to send backwards signals to this applicator and associating somehow the current input to the long memory.

    Also the inputs layer from normal sensors go to indicate actions as usual but also go to long_memory > reward_applicator to get a closed loop system.

    I will not be able to give a reward for walking towards the food but if the long memory + reward helps to reach the food by chance, the neurons receive their energy and it is recorded. Otherwise... natural selection.

    or something similar :D

  • updating specs

    3drobert12/29/2021 at 19:13 0 comments

  • options...

    3drobert12/24/2021 at 10:48 0 comments

    Plot and more things...

    I have already added softmax but still I need to add momentum and regularization

  • NGBrain - Blender. Virtual camera

    3drobert12/22/2021 at 04:56 0 comments

  • Blender training

    3drobert12/22/2021 at 03:31 0 comments

    Now a virtual camera :)

  • NGBrain Blender pendulum connection

    3drobert12/21/2021 at 18:05 0 comments

    still missing to pass the action

View all 77 project logs

Enjoy this project?

Share

Discussions

dearuserhron wrote 09/14/2021 at 21:17 point

The idea of using multiple small MCUs instead of big one always was on my mind. The hardest part is to get them talk to each other.

  Are you sure? yes | no

3drobert wrote 09/14/2021 at 21:40 point

I try to divide the work as much as possible so that the master only has to listen to the data of its associated sensor from the slaves and send it all via WIFI to the PC. And receive the action also via WIFI and indicate it to the slave that has that action associated with it.

Even one of the 3 MCUs of the slaves is just to coordinate the other two which are one MCU for the gyroscope and the other MCU for the servo. So that the information is quickly available and flows without much of a jam in making calculations when the master requests things from the slaves.
I have activated PLL to achieve 48MHz too

  Are you sure? yes | no

kavinjhon8 wrote 08/09/2021 at 06:19 point

Thanks for sharing this project details. I also work on different projects. Feel free to visit: https://ihomedental.com/

  Are you sure? yes | no

Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates