"рдК рдареНрдпрд╛рдХреНрдХреИ рд╕рд╛рд░рд╛рдкреЛрднрд╛ рдЬрд╕реНрддреИ рдЫреЗред" "рдХреЛ рд╕рд╛рд░рд╛рдкреЛрднрд╛?" "рдорд╛рд░рд┐рдпрд╛ рд╕рд╛рд░рд╛рдкреЛрднрд╛ рдХреНрдпрд╛ рддред" "рдХреЛ рдорд╛рд░рд┐рдпрд╛ рд╕рд╛рд░рд╛рдкреЛрднрд╛?" "рдЙрд╣реА рдХреНрдпрд╛ рдд рдЯреЗрдирд┐рд╕ рдЦреЗрд▓рд╛рдбреА, рд░реВрд╕реАред" "рдП рддреНрдпреЛ рдкреЛ?" "рдХрд╕рд░реА рдЫреЗ рдЙрд╕реНрддреИ? рдЙрдЪрд╛рдЗ рд╣реЗрд░реНрджрд╛ рдд рдорд╛рд░рд┐рдпрд╛ рд╕рд╛рд░рд╛рдкреЛрднрд╛рдХреА рдЖрдзреА тАж
Blog
Collection of blog posts on various topics on science, society programming, physics etc.
In the [previous post][fnn] we discussed how to make functional Neural Network (NN) with julia. In [another post][nn-package] we discussed how to package our NN into an independent julia package. As тАж
In a seris of previous posts we, described how to make a [fully functional Neural Network][fnn] in julia. Lets create a package so that we can import the neural network in julia as a regular package тАж
Say you wrote an ingeneous julia function ```julia magic(x) = incredible(x) ``` And you want this to be available to other people. Then the first thing to do is to create a file called `Magic.jl` тАж
After a series of [previous posts][activation-func] we hav learned the key steps of making a Machine Learning: 1. [Gradient Descent][basicnn] 2. [Back Propagation][backprop] 3. [Adding Multiple тАж
As we saw in [previous post][multinode] addition of any number of layers and any number of nodes will only be able to model a linear functions. If we want our network to also be able to learn non тАж
In the previous two posts we have already seen how to construct a single neuron neural network with or without hidden layer. If we want to input multidimensional input and get multidimensional output тАж
## Setup Similar to [last post](/posts/2022/05/basic-neural-network-with-julia/), where we made a basic neural network with just one neuron and no hidden layer, we will build a two neuron and a тАж
In this post I will try to describe building a basic regression model with gradient descent. This forms a very basic prototype of neural network. This by no means is a full fledged neural network, тАж