Introduction
Deep learning (deep structured learning, hierarchical learning or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data. TensorFlow is a popular, new and comprehensive library for deep learning. Students will learn to build deep learning applications using Tensorflow in this course.
Course Outline
- Getting Started
- Introduction to TensorFlow
- Installing and Running TensorFlow
- Basic Tensorflow Operations
- Constant
- Graph Operation
- Math
- Matrix
- Placeholder
- Variable
- Datasets
- Iris Flower Dataset
- MNIST Handwritten Digits Dataset
- CIFAR Image Dataset
- One Hot Encoding/Decoding
- Split Dataset to Training/Testing
- Machine Learning on TF
- TF Graph Model
- Loss Function
- Optimizer
- Training
- Metrics
- Neural Network (NN)
- What is Neural Network
- Activation Functions
- Create a Deep Neural Network on TF
- TensorFlow Playground
- Tensorboard
- What is Tensorboard?
- Visualize a Tensorboard Graph
- Output Data to Tensorboard
- Convolutional Neural Network (CNN)
- What is CNN?
- CNN Architecture
- Convolution
- Pooling and Stride
- Dropout
- Recurrent Neural Network (RNN)
- What is RNN?
- How to train a RNN
- Long Term Dependencies
- LSTM Cell
- GRU Cell
- Keras
- What is Keras?
- Install Keras
- Neutral Network with Keras
- Inception V3 Transfer Learning
- TFLearn
- What is TFLearn?
- Install TFLearn
- Neutral Network with TFLearn
5