Join Leonardo De Marchi and take a look at Deep Learning concepts with Keras by analysing an image recognition project and learning to develop the model from start to finish. Examine the business needs of a project and design a solution, create a multi layer network and get an intro to some more sophisticated practices including implementing different types of networks for image recognition, using dropouts and random noise to improve results, selecting the proper architecture and using pre-trained models.

This course is part of Coding the World - A training series co-organized by Zenika and Skills Matter and will be offered virtually over 4 half‑day sessions from February 8 to 11, 2020.

Programme:

Day One

DL Basics

• Introduction to Deep Learning
• Key ML concepts and terminology
• Examples in industry and research
• Formalizing your own DL problem

Feedforward Neural Networks

• Training neural networks, optimization methods, error back-propagation
• Introduction to Keras and Pytorch

Lab 0: Getting Started with GPUs and cloud computing

• Quickly set up a machine with Deep Learning and NVIDIA Docker
• Set up additional libraries like keras-viz
• Quick demo on how to use tensorboard
• TensorFlow, Keras and Pytorch
• Introduction
• Overview
• Pros and Cons
• How to use the right tool

Lab 1: Getting Started with Keras

• Basic concepts
• Terminology
• Exercise

Lab 2: Implement and train a feed-forward neural network in Keras

• Tackling the problem of facial expression recognition
• Convolutional Neural Networks (CNNs)
• Understanding the convolutional architecture
• Convolutional and pooling layers
• Applications to image classification

Lab 3: Implementing CNN using Keras A

• Extending a feed-forward network with convolutional and pooling layers
• Using CNNs for image dataIntroduction to Docker Compose
• Introduction to Docker Swarm
• Introduction to Kubernetes
• Docker Secrets

Day Two

Lab 3 continued: Implementing CNN using Keras B

• Recap of the main concepts
• Lab solutions

Recurrent Neural Networks

• Understanding recurrent architectures
• Elman, LSTM and GRU units
• Bi-directional architectures
• Combining RNNs with convolutional and feed-forward layers
• Applications to speech
• Biological sequences and information retrieval

Lab 4: Implementing RNNs using Keras

• Implementing and training RNNs using LSTM units on a simple natural language processing task

Practical tricks of the trade

• Using pre-trained networks
• Transfer learning
• Visual debugging of DNNs

Lab 5: Practical tricks of the trade

• Practicing concepts of the previous theoretical session

Closing remarks and feedback

• Introduction to Multi-Armed bandit and Reinforcement Learning

More: https://skillsmatter.com/courses/754-deep-learning-fundamentals-with-leonardo-de-marchi

About the Author - Leonardo De Marchi

Leonardo De Marchi is Lead Data Scientist for Badoo, the World's largest dating website, and is a consultant for the European Union Commission, helping to develop a European strategy for Big Data. He holds a Master's Degree in Artificial Intelligence and has worked as a Data Scientist with the New York Knicks, and Manchester United FC, as well as large social networks including JustGiving.

Leo has extensive experience in a wide variety of ML problems, such as anti-spam, revenue optimization and image recognition. He is the founder of London Artificial Intelligence, and has been a speaker at Predictive Analytics World - the premier machine learning conference.

Audience

If you are an administrator or developer and you want to learn how to administer and build enterprise-grade production systems using Docker, this Docker course is for you!

More about Coding the World

Coding the World is a joint venture from Zenika and Skills Matter to empower and upskill software professionals around the globe during this unprecedented time.

With Coding the World, Skills Matter and Zenika are adapting the expert-led training both companies previously offered in cities like London, Singapore and Montreal, and making them accessible to the world via live workshops hosted online throughout 2020 and 2021.

Learn More about all the upcoming courses & workshops here - https://skillsmatter.com/go/coding-the-world

Know more about Zenika Singapore here - https://www.zenika.sg/

TERMS & CONDITIONS

• Zenika Singapore reserves the right to amend these Terms and Conditions at any time.
• Order cancellations and order amendments are not allowed.
• Please note that Zenika Singapore reserves the right to cancel or re-schedule training if necessary. In the unlikely case that Zenika Singapore must cancel or reschedule any training, Zenika Singapore will inform all attendees one week in advance and will endeavour to provide an alternative date.
• There will be strictly no refunds for no-shows.
• Zenika and Skills Matter owns sole copyright of all content.