Deep Learning using TensorFlow

This repository contains implementations of deep learning solutions using Tensorflow. Best practices to train a neural network for a deep learning applications. In most cases, the notebooks lead you through implementation of models such as convolutional networks, recurrent networks, long short-term memory and GRUs. There are other topics covered such as weight intialization and batch normalization.

Table Of Contents

Objectives

• Introduction:

  • Learn best practices for using TensorFlow, a popular open-source machine learning framework

  • Build a basic neural network in TensorFlow

  • Train a neural network for a computer vision application

  • Understand how to use convolutions to improve the neural network

• Convolutional Neural Network:

  • Handle real-world image data

  • Plot loss and accuracy

  • Explore strategies to prevent overfitting, including augmentation and dropout

  • Learn transfer learning and how learned features can be extracted from models

• Natural Language Processing:

  • Build natural language processing systems using TensorFlow

  • Process text, including tokenization and representing sentences as vectors

  • Apply RNNs, GRUs, and LSTMs in TensorFlow

  • Train LSTMs on existing text to create original poetry and more

• Sequences, Time Series and Prediction:

  • Solve time series and forecasting problems in TensorFlow

  • Prepare data for time series learning using best practices

  • Explore how RNNs and ConvNets can be used for predictions

  • Build a sunspot prediction model using real-world data