Deep Learning using Tensor Flow
Overview
Traditional neural networks depend on shallow nets consisting of one input, plus one hidden layer and one output layer. Deep-learning networks are very different from these ordinary neural networks as they have more hidden layers. Such kinds of nets are capable of determining unseen structures within unlabelled and unstructured data which establishes the vast majority of data in the world. TensorFlow is one among the hand-picked libraries to implement deep learning. Nodes present in the graph signify mathematical operations, while the edges signify the multidimensional data arrays or tensors that flow between them.Duration
3 Days
Pre-Requisites
- Basic programming knowledge in Python
- Concepts of Machine Learning
Course Outline
- HelloWorld with TensorFlow
- Linear Regression
- Nonlinear Regression
- Logistic Regression
- Activation Functions
- CNN History
- Understanding CNNs
- CNN Application
- Intro to RNN Model
- Long Short-Term memory (LSTM)
- Recursive Neural Tensor Network Theory
- Recurrent Neural Network Model
- Applications of Unsupervised Learning
- Restricted Boltzmann Machine
- Collaborative Filtering with RBM
- Introduction to Autoencoders and Applications
- Autoencoders
- Deep Belief Network