@homeopathicfossil-fuels4789
Dude you got the degree I wanted and seemingly living the life of my dreams, good going! Awesome! Aerospace engineer that builds artificial hardware neurons on breadboard in his pasttime, that is so cool, subscribed because this is 1:1 my interests.
@J.D-g8.1
Very cool. To make it more similar a biologic neuron we need: -autoreceptors; ex; on a excitatory cell released neurotransmitter can bind to the post synaptic receptor which depolarize the post synaptic cell and cause an action potential, but it can also bind to pre-synaptic receptors to inhibit further release of transmitter. Autoreceptors/pre synaptic rec. are thus inhibitory. The cell/neuron will continously alter its expression of autoreceptors which in turn regulate how likely it is to propagate the signal to the next cell. Whether we actually need autoreceptors on artificial neurons idk, but as opposed to 2 neurons acting on a 3rd post synaptic neuron where the combined effect is either inhib. or stim., autoreceptors add the ability of the excitatory neuron becoming "more" or "less" excitatory depending on various input (hormones, etc) This is only needed in artificial neurons if we want f.ex to simulate "feelings"; i.e when "scared" the excitatory neuron has a more powerful stim. effect than when "calm".
@Magic_Tee
I think that everyone who starts working with neural networks should start with this. I may be old-fashioned, but it’s hard for me to take seriously anyone who considers himself an "expert" in the field of neural networks, having never held a transistor in his hands and has no idea about the structure of a biological prototype.
@ltkdt
This video deserves a lot more views. It is educational and amazing to see someone stimulating nerves with only eletronics components you can easily buy!
@Enigma758
Hi, This is very cool, you created a novel dynamic system that self activates! It's also aesthetically pleasing. As usual, I have a few questions and comments: 1. Is the diode really necessary since I don't think you need to protect against negative voltages? Maybe its purpose is to simulate an activation threshold at the "knee". 2. Is the self-activating pattern somewhat stable and deterministic, or somewhat random and chaotic? It's hard to tell from the video, even when slowing it down. Since transistors vary as they heat up, I would imagine there would be some variation. 3. Does the system form a complete loop (i.e. "recurrent")? In other words is the "first" neuron itself triggered by another neuron or is it just set to a fixed potential? 4. I could see that some configurations might settle out, stop cycling and reach a stable pattern. Have you experienced that? Have you determined the conditions for continous activation? Did you have to "tweak" it to get a stable active pattern? 5. BTW, I like your neuron video, did you produce that yourself? It's a very good animation! (Sorry I have so many questions 😊) Thanks!
@franciscomorales8102
watching your video gave me an idea... before sending you my thoughts, I am going to research a few things and do some brainstorming. I am definitely interested in the way neurons work, and this opened a whole new was for me to think about it!! thanks!
@peterward6465
I followed the setup at 5:25 but the blue light seems to turn on without me pressing the button. Could the resistors be the cause? If so, could you please tell me what the values are? I'm having a hard time seeing the colors (and still learning how to read schematics). Thanks
@rockieroux5966
really appreciate it buddy , I learned something new, keep doing the great work kudos
@deepstories32
our human body is way more advance then we think ,its really amazing to learn all these
@computer-x6t
imagine , this is the first thing our children do when you give them a kit
@mtg-7452
Hi ,Nice vidoes.Can you also do some more breadboard circuits using transistors or ics.Its so coool
@alexsaptetrei
Way above my pay grade. Kudos
@homeopathicfossil-fuels4789
Polarizing material between the optocouplers? You can do a lot of bioanalogous things with the raw optocoupler from a pair of LED's thing, you could even do volume transmission. Also opamps and memristors work great for creating spiking neurons.
@개구리-t4f-f3h
It looks very funny, and I think this is true artificial intelligence! If you use servo motors and sensors to create something that actually interacts with the environment, that's going to be crazy. I hope that this field will develop so that synaptic plasticity can be implemented and learning can be done
@Oh-ou4lp
I havent built it yet ut was thinking if you added a mic input to it so the firing pattren can change based on tone input to simulate hearing in diffrent areas of the network. so as you speak to it you can see what areas fire and come up with a logic respose based on the amp of audio wave in to make a response. Like if it hears a loud noise it chould have a reaction like fear or activates the other networks to try to figure out if it is good or bad and if good respond 1 if bad respond 2 if undeceiced back to listen.Just my random thoght on it. very cool to see the workings of it
@erikrodriguez7112
A fascinating design. Very simple. I would LOVE to play with it. What transistors do you use in this? Other thoughts - ReLU can be used as a function of the neuron to control and adjust firing frequency while Tanh is very practical in functioning as the transfer function. As for the resistors to control the triggering event as well as the weights in the synapses, though this is not a pure analog solution - but is suitable until cost effective and functional memristors are available - consider the use of something like a digital potentiometer such as the MCP4012T. This would then make a dynamic neuron that would very closely emulate the function of biological neurons that is capable of adjusting while functioning and not needing manual adjusting of resistors. A simple computer - such as a raspberry pi - would be able to calculate feedback based on training set errors into the analog neural network. Another more advanced concept would be to incorporate a 'routing' system for analog signals to define connections from neuron to synapse - thus enabling a DNN to evolve over time given suitable numbers of analog neurons and synapses. Something to be considered if the above mentioned neuron/synapse designs can be proven then fabricated on chips.
@arthence
This is everything i want to study. Thank you
@PraveenKushinpi
what a video , what a explanation
@gunnertheguy7287
I’m confused, so what do you used the neurons for?
@БидонКадыкавич-х2ц