I have implemented some AI projects from scratch implementation without explicit use of the built-in-libraries and thus added to this repo.
-
Updated
Aug 6, 2020 - Jupyter Notebook
I have implemented some AI projects from scratch implementation without explicit use of the built-in-libraries and thus added to this repo.
Deep Learning model for predicting success after donation coded in Google Colab
Developed Neural Network (NN) having one hidden layer, two hidden layers and four hidden layers, besides the input and output layers. Tested with Sigmoid, tanh and ReLu activation function. Used Scikit learn for pre-processing data.
Revising concepts of CNN by building them from scratch using NumPy.
Time series forecast using RNN and LSTM
2nd Project of Course 'Machine Learning' of the SMARTNET programme. Taken at the National and Kapodistrian University of Athens.
Exploration of teamwork in neural networks
Feed Forward Neural Network to classify the FB post likes in classes of low likes or moderate likes or high likes, back propagtion is implemented with decay learning rate method
Neural Network implementation from scratch along with its analysis with different type of activation function and with variation in hidden layer size and depth.
An activation function in the context of neural networks is a mathematical function applied to the output of a neuron. The purpose of an activation function is to introduce non-linearity into the model, allowing the network to learn and represent complex patterns in the data.
quick 'n' dirty neural network (for practical use)
Simple self-written ANN powered by NumPy to classify handwritten digits of the famous MNIST Dataset. ✍️
Neural-Net-Numpy(NNN) is a simple python package for training neural networks using only numpy components
Advance Machine Learning (CSL 712) Course Lab Assignments
Multi-Layer Neural Network
Add a description, image, and links to the tanh topic page so that developers can more easily learn about it.
To associate your repository with the tanh topic, visit your repo's landing page and select "manage topics."