This course is designed for Software Architects, Developers, Data Engineer, Analyst and Machine Learning Engineer.

1. Basic knowledge of command line Linux editors (VI / nano)
2. Basic understanding of Machine Learning
3. Python experience as applied to the Data Science/Machine Learning space

Course Outline:

1. History and Background of AI and ML
2. Compare AI vs ML vs DL
3. Introduction to neural networks
4. The math behind neural networks
5. Back propagation
6. Understanding the intuition behind neural networks

Introducing TensorFlow

1. TensorFlow intro
2. TensorFlow Features
3. TensorFlow Versions
4. GPU and TPU scalability
5. Lab: Setting up and Running TensorFlow
6. The Tensor: The Basic Unit of TensorFlow
7. Introducing Tensors
8. TensorFlow Execution Model
9. Lab: Learning about Tensors

Introducing Perceptrons

1. Single Layer Linear Perceptron Classifier With TensorFlow
2. Linear Separability and Xor Problem
3. Activation Functions
4. Softmax output
5. Backpropagation, loss functions, and Gradient Descent
6. Lab: Single-Layer Perceptron in TensorFlow

Hidden Layers: Intro to Deep Learning

1. Hidden Layers as a solution to XOR problem
2. Distributed Training with TensorFlow
3. Vanishing Gradient Problem and ReLU
4. Loss Functions
5. Lab: Feedforward Neural Network Classifier in TensorFlow

High-level Tensorflow: tf.learn

1. Using high-level TensorFlow
2. Developing a model with tf.learn
3. Lab: Developing a tf.learn model

Convolutional Neural Networks in Tensorflow

1. Introducing CNNs
2. CNNs in Tensorflow
3. Lab: CNN apps

Introducing Keras

1. What is Keras?
2. Using Keras with a Tensorflow Backend
3. Lab: Example with a Keras

From Deep Neural Networks to Deep Learning

1. Understanding unstructured data
2. Image recognition
3. Introduction to Convolutional Neural Networks (CNN)
4. Convolutional layers
5. Pooling layers
6. Fully-connected layers
7. Hands-on: Using TensorFlow to create a CNN
8. Hands-on: Image recognition project

Image processing elements

1. Convolutions
2. Pooling
3. Edge Detection
4. De-noising

Time series processing and forecasting elements

1. Traditional Time Series forecasting with ARIMA models
2. Defining Autocorrelation
3. Understanding the Dickey-Fuller Test

Forecasting with TensorFlow and Keras

1. Using RNN and LSTM in time series prediction.
2. Validation and metrics of Time Series Prediction models

References and Next steps

Structured Activity/Exercises/Case Studies:

1. TensorFlow Hands-on
2. Keras Hands-on
3. Using TensorFlow to create an CNN
4. Image Recognition project

Training material provided: Yes (Digital format)