[ Training ] Applied Machine Learning


This course is for professionals with a basic understanding of Machine Learning who wish to learn the practical aspects of making AI and NN work well. The course includes making real models in tensorflow and keras and covers deployment on deep models and practical projects in NLP, object-recognition and reinforcement learning.

[ Trainers ]

Key instructors of the course will be Vazgen Hakobjanyan and Mikayel Samvelyan.

Select topics to be covered by practicing professionals from YerevaNN, AUA, SignalNPixomatic, and Fimetech.

Vazgen Hakobjanyan

YerevaNN, Teamable, SmartGateVC

Please reload

Mikayel Samvelyan

Oxford University

Please reload

[ Key information ]

Application opening: April 5

Application deadline: May 31

Start date: June 4

Course duration: 2.5 months (36 lessons, 2 hours each)

Lecture days: Mon, Wed, Sat

Course fee: AMD500k

The course follows the Intro to Machine Learning course launched on May 15.

Course participants will be selected by test and interview.

[ Prerequisites ]

Programming: basic Python programming skills, with the capability to work effectively with data structures.
Mathematics: linear algebra, probability theory, and calculus. 
Machine Learning: understanding how to frame a machine learning problem, including how data is represented.

[ Curriculum ]

  • Neural Networks

  • Regularization, Validation

  • Optimization

  • Hyperparameter tuning

  • Convolutional Neural Networks

  • Deep convolutional models: case studies

  • Object Detection

  • Special applications: Face recognition & Neural style transfer

  • Recurrent Neural Networks

  • Natural Language Processing & Word Embeddings

  • Advanced topics in NLP

  • Speech Recognition and Text to Speech

  • Reinforcement Learning (Value-based methods)

  • Reinforcement Learning (Policy-based methods)

  • Unsupervised Learning, Autoencoders

  • Generative Adversarial Networks

© 2018 by SmartGate Seed Fund I Partners, LLC and CATALYST Foundation