somnibyte / mlkit Goto Github PK

Hi,
For iOS projets it's will be great to make your component Carthage compatible

Take a look at these articles:

• Ruthlessly Simple Dependency Management with Carthage
• Carthage Tutorial: Getting Started
• Making Carthage-compatible Frameworks with Swift
• Swift Cross Platform Framework (section Configure targets for Carthage) 👍

On your README.md add on top and add section for the installation with Carthage.

First off, what you are working on here is immensely impressive. I just wanted to point out somethings I have learned implementing NN's myself and pass along any possible insight.

If I understand the structure currently, you have an overarching NN class that contains references to a layer class which itself contains references to your final neurons. A possible simplification you may want to look into is to completely eliminate the neurons class and rather represent each layer in the network as a single 2D vector/tensor with dimension mxn where m is the number of neurons in the layer and n is the number of neurons in the previous layer. With this approach you can calculate forward propagation at each layer by taking said layers mxn vector/tensor and dotting it with the previous layers output vector/tensor, resulting in an output vector/tensor that can either be used to feed into the next layer or be used as the output of the network as a whole.

So while this approach simplifies your forward propagation, it also simplifies your back propagation as you can use the same dot product to go back through your layers and calculate the amount by which you should adjust the weights. If you have a layers input vector, it's output error as a vector, and a vector containing the derivative of the activation function at each output, the amount each weight should be adjusted is the dot product of the input vector and (output error vector * derivative value error). Hopefully I explained that well enough, apologizes if not :(

You have eluded to a desire to implement some performance increases using Metal down the road and I feel you may also find dot products are ideal for parallelization on a GPU.

Any who, feel free to ignore this but I just wanted to pass it along. Excited to see where this project ends up!

I left the initial weights as the default values but it doesn't set the weights after that

        let initial_weights = Matrix<Float>(rows: 3, columns: 1, elements: [-100000.0, 1.0, 1.0])

        let weights = try! polynomialModel.train([timestamp,weekday], output: output_data, initialWeights: initial_weights, stepSize: Float(4e-12), tolerance: Float(1e9))

I've got 2 features like the Polynomial Regression Usage guide.