Deep Learning Specialist Certificate

1-Learning Methodology

• Instructor-Led Classroom Training (ILT).

2-Prerequisites:

• Machine Learning Specialist Certificate

3-Training Program Description:

• Deep learning is driving advances in artificial intelligence that are changing our world. Enroll now to build and apply your own deep neural networks to challenges like image classification and generation, time-series prediction, and model deployment.
• you’ll master fundamentals that will enable you to go further in the field, launch or advance a career, and join the next generation of deep learning talent that will help define a beneficial, new, AI-powered future for our world. You will study cutting-edge topics such as Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Generative Adversarial Networks, and Network Deployment, and build projects in Keras and NumPy

• In this course, you practice with real-life examples of Deep learning and see how it affects society in ways you may not have guessed!

• Length of Program: 5 weeks

• Who is this class for?
  • This course is primarily for individuals who are passionate about the field of data science and data analysts and who are aspiring to apply machine learning and Deep Learning in their business, industry or research.
  • Developers and Software Engineers
  • Analytics Managers and Professionals
  • Statisticians with an interest in Machine and deep learning

• What you will learn
  • Implement Neural Networks from scratch
  • using frameworks like Keras.
  • Build convolutional networks, recurrent networks and generative adversarial networks
  • Introduce major deep learning algorithms, the problem settings, and their applications to solve real world problems

4-program outcomes:

• Identify the deep learning algorithms which are more appropriate for various types of learning tasks in various domains.
• Implement deep learning algorithms and solve real-world problems

5-Projects

This program is comprised of many career-oriented projects. Each project you build will be an opportunity to demonstrate what you’ve learned in the lessons. Your completed projects will become part of a career portfolio that will demonstrate to potential employers that you have skills in data analysis and feature engineering, machine learning algorithms, and training and evaluating models.

One of our main goals at EAII is to help you create a job-ready portfolio of completed projects. Building a project is one of the best ways to test the skills you’ve acquired and to demonstrate your newfound abilities to future employers or colleagues. Throughout this program, you’ll have the opportunity to prove your skills by building the following projects

Building a project is one of the best ways both to test the skills you’ve acquired and to demonstrate your newfound abilities to future employers. Throughout this program, you’ll have the opportunity to prove your skills by building the following projects:

• Project 1: Build your Own Neural Net from Scratch
• Project 2: Dog Breed Recognition
• Project 3: Image Classification
• Project 4: Face-Recognition
• Project 5: Cancer Detection
• Project 6: Kaggle Competitions Projects
• Capstone Project

6-Training Program Curriculum:

I-Deep Learning Topics

• Neural Networks
  • INTRODUCTION TO NEURAL NETWORKS
  • IMPLEMENTING GRADIENT DESCENT
  • TRAINING NEURAL NETWORKS
  • DEEP LEARNING WITH KERAS

• Convolutional Neural Networks
  • INVARIANCE, STABILITY
  • CLOUD COMPUTING
  • CONVOLUTIONAL NEURAL NETWORK
  • PROPERTIES OF CNN REPRESENTATIONS: INVERTIBILITY, STABILITY, INVARIANCE.
  • WEIGHT INITIALIZATION
  • AUTOENCODERS
  • VARIATIONAL AUTOENCODERS
  • VARIABILITY MODELS (DEFORMATION MODEL, STOCHASTIC MODEL).
  • SCATTERING NETWORKS
  • GROUP FORMALISM
  • SUPERVISED LEARNING: CLASSIFICATION.
  • COVARIANCE/INVARIANCE: CAPSULES AND RELATED MODELS.
  • CONNECTIONS WITH OTHER MODELS: DICTIONARY LEARNING, LISTA.
  • OTHER TASKS: LOCALIZATION, REGRESSION.
  • EMBEDDINGS (DRLIM), INVERSE PROBLEMS
  • EXTENSIONS TO NON-EUCLIDEAN DOMAINS
  • DYNAMICAL SYSTEMS: RNNS.

• Recurrent Neural Networks
  • RECURRENT NEURAL NETWORKS
  • LONG SHORT-TERM MEMORY NETWORK
  • IMPLEMENTATION OF RNN & LSTM
  • HYPERPARAMETERS
  • EMBEDDINGS & WORD2VEC

• Generative Adversarial Networks
  • GENERATIVE ADVERSARIAL NETWORK
  • MAXIMUM ENTROPY DISTRIBUTIONS
  • DEEP CONVOLUTIONAL GANs
  • PIX2PIX & CYCLEGAN

• Model Deployment
  • INTRODUCTION TO DEPLOYMENT
  • DEPLOY A MODEL
  • MODEL MONITORING
  • UPDATING A MODEL