Deep-Learning-with Neural Networks
(URL: https://github.com/rickhagwal/Deep-Learning-with-Neural-Networks/tree/Basic-TensorFlow-Example )
1.) Creating neural network with one layer in TensorFlow and Google Colab notebook.
Example- Predicting House Prices (Predict_House_Prices_(1).ipynb)
In this exercise, i tried to build a neural network that predicts the price of a house according to a simple formula.
So, imagine if house pricing was as easy as a house costs 50k + 50k per bedroom, so that a 1 bedroom house costs 100k, a 2 bedroom house costs 150k etc.
Created a neural network that learns this relationship so that it would predict a 7 bedroom house as costing close to 400k etc.
2.) INTRODUCTION TO COMPUTER VISION (Creating neural network with multiple layers)
Example - Predict 99% accuracy for handwriting datset (MNIST_classifier_to_test_handwriting.ipynb)
In this exercise, classification using dataset called MNIST ahs been done, which has items of handwriting -- the digits 0 through 9. MNIST dataset is already present in Keras library.
Written MNIST classifier that trains to 99% accuracy or above, and does it without a fixed number of epochs -- i.e. it should stop training once you reach that level of accuracy.