I followed RaffK project to its completion and did much more feature development such as complete chat feature. I created a lot of Modern and screaming Future C++, it is sort of crazy. This ChatGPT2 animation experiment involved training chatgpt2 on scrolling Shakespeare 1000 times using SGD with a learn rate of 0.0002. After SGDContinue reading “ChatGPT2 Animator Adventure”
Category Archives: Ai
Golden Ticket Exploration
So, if we have made some network, initial state, not like this one: And we applied typical backpropagation training process using SGDx0.002, on MNIST, we could get an image somehow like this: This is an image of a trained Golden Ticket than I created which is not Dyson Hatching and I will describe later. WhatContinue reading “Golden Ticket Exploration”
Dyson Hatching Golden Ticket
Nick: so now it is time to make use of the voronoi diagram. To begin, I want to calculate the average slope of the edges of each cell ChatGPT: The slope of a line is typically calculated as the difference in the y-coordinates of two points divided by the difference in the x-coordinates of thoseContinue reading “Dyson Hatching Golden Ticket”
ChatGPT and Golden Ticket pt 3
ChatGPT: Yes, that’s correct. Once you have a Delaunay triangulation, generating the corresponding Voronoi diagram is relatively straightforward. In a Voronoi diagram, each cell consists of all the points that are closer to a particular site (i.e., an input point) than to any other. This makes the Voronoi cell the dual of the Delaunay triangle,Continue reading “ChatGPT and Golden Ticket pt 3”
ChatGPT and Golden Ticket 2
Nick: We shall now examine polygon creation ChatGPT: Okay, the next step is to create the polygon that is the hole created by the bad triangles. This polygon is going to be filled by new triangles formed by the vertex v and each edge of the polygon. First, you need to extract all the edgesContinue reading “ChatGPT and Golden Ticket 2”
ChatGPT and Golden Ticket
So, some long time ago when ChatGPT first came out, the first really cool thing I somehow made, was my Golden Ticket algorithm. I’m going to discuss the Golden Ticket code and the production method I used with the original ChatGPT. This is an easy task because my chat history is saved by Open Ai.Continue reading “ChatGPT and Golden Ticket”
The smallest xor network and lottery ticket
I am creating networks that are: two input nodes, x*y hidden nodes, and one output node. The ability to create these networks has to do with some odds which are based on the initial state of the starting network pool. I have a pool of 2000 networks which are randomly generated, and I try toContinue reading “The smallest xor network and lottery ticket”
Non-Convolutional Image Recognition
I have had some difficulty determining numbers for training times for mnist, so I am going to post some of mine, and also discuss what my network is doing. So far in my work on mnist, I have generated a convergent network. Using cpu only, ryzen 7 1700, I train a convergent network in underContinue reading “Non-Convolutional Image Recognition”
Visualizing network training
Here is a video of where my project is at, Basically, it provides a graphical visualization of the network weights. I am going to experiment with generating and examining this sort of image through training. In this video, the network is training on six problems, and it slowly learns for about 45 seconds. After that,Continue reading “Visualizing network training”
Intelligent sequences of numbers
Since a large property of a neural network is indeed its initial or current random state, maybe we can consider this entire state as just a vector of randomly generated values. In reality, that’s what it is on the computer. Each of these values is generated via a random number generator in a specific sequence.Continue reading “Intelligent sequences of numbers”
Spot C++ 