Overview of Deep Learning with TensorFlow
Traditional neural networks depend on shallow nets, consisting of one input, one hidden layer and one output layer. Deep-learning networks are very different from these ordinary neural networks having more hidden layers, or so-called more depth
Such kinds of nets are capable of discovering unseen structures within unlabelled and unstructured data (i.e. images, sound, and text), which establishes the vast majority of data in the world
TensorFlow is one among the finest libraries to implement deep learning. Nodes present in the graph signify mathematical operations, while the edges signify the multidimensional data arrays /tensors that flow between them.
Duration
3 Days
Prerequisite for Deep Learning with TensorFlow
- Basic programming knowledge in Python
- A few Concepts about Machine Learning
Course Outline for Deep Learning with TensorFlow
Introduction to TensorFlow
- HelloWorld with TensorFlow
- Linear Regression
- Nonlinear Regression
- Logistic Regression
- Activation Functions
Convolutional Neural Networks (CNN)
- CNN History
- Understanding CNNs
- CNN Application
Recurrent Neural Networks (RNN)
- Intro to RNN Model
- Long Short-Term memory (LSTM)
- Recursive Neural Tensor Network Theory
- Recurrent Neural Network Model
Unsupervised Learning
- Applications of Unsupervised Learning
- Restricted Boltzmann Machine
- Collaborative Filtering with RBM
Autoencoders
- Introduction to Autoencoders and Applications
- Autoencoders
- Deep Belief Network