Training – Deep Learning using TensorFlow and Keras (IOT305)

Deep Learning is a branch of machine learning that utilizes neural networks. But how does a neural network work, and how does deep learning solve machine learning problems? In this workshop, you will learn how to get started with deep learning using one of the most popular frameworks for implementing deep learning – TensorFlow. You will also use another API – Keras, which is built on top of TensorFlow, to make deep learning more user-friendly and easier.

Topics

Introduction to Neural Networks
Deep Learning and Neural Networks
- Perceptron and Neural Networks
- Layers, Weights and Biases
- Activation Functions
  - Softmax
  - ReLu
  - Leaky ReLu
- Back Propagation
- Loss Functions
  - Binary cross entrophy
  - Categorical cross entrophy
  - Mean-squared error
- Optimizers – Gradient Descent, RMSprop, Adam
- Evaluating Performance
Common Types of Neural Networks
- Convolutional Neural Network (CNN)
- Recurrent Neural Network (RNN)
What is TensorFlow?
- What is a Tensor?
- Basic TensorFlow Operations
  - Graph and Session
  - Mathematical Operations
  - Matrices
  - Variables and Constants
  - Placeholders
  - Visualizing your graph using TensorBoard
  - Building a Perceptron using TensorFlow
Using Keras with TensorFlow
- Image Classifications
- Text Classifications
- Custom Image Recognizer
Transfer Learning
- What is Transfer Learning?
- Using pre-trained models
- Fine-tuning pre-trained models

Prerequisites

Basic programming experience
Understanding of basic object-oriented programming concepts

Hardware

Mac / Windows laptop

Software

Anaconda (Python 3.7)
Visual Studio Code

About the course

Duration – 2-day
Trainer – Wei-Meng Lee
Standard price – 449 Eur + VAT
Date – to be announced (if you’re interested, please contact edgars@devclub.lv)
Location – online

About Wei-Meng Lee

Wei-Meng Lee is a technologist and founder of Developer Learning Solutions (http://www.learn2develop.net), a technology company specializing in hands-on training on the latest mobile technologies. Wei-Meng has many years of training experiences and his training courses place special emphasis on the learning-by-doing approach. His hands-on approach to learning programming makes understanding the subject much easier than reading books, tutorials, and documentations. His name regularly appears in online and print publications such as DevX.com, MobiForge.com, and CoDe Magazine.

Some of Wei-Meng Lee’s Clients