Certificate In Machine Learning & Deep Learning

The Programme

Machine Learning & Deep learning computer algorithms go through a similar process to a child learning to recognise a dog. Each algorithm in the hierarchy performs a nonlinear transformation on its input before generating a statistical model as an output. Iterations continue until the result is accurate enough to be useful. The word deep was motivated by the amount of processing layers that data must flow through. The programme will expose you to various aspects of computer networking, software development and more.

Programme Objective

  • Demonstrate Activation functions and Optimizers in detail with hands-on 
  • Demonstrate intuitively convolutional neural networks for image recognition 
  • Design and construct a neural network from simple to more accurate models 
  • Understand recurrent neural networks, its applications and learn how to build these solutions 
  • Understand hyper-parameters and tuning. 

Pogramme Learning Outcome

  • Articulate the core architecture and API layers TensorFlow 
  • Construct a computing environment and learn to install TensorFlow 
  • Develop TensorFlow graphs required for everyday computations 
  • Use logistic regression for classification along with TensorFlow 
  • Develop, design and train a multilayer neural network with TensorFlow 
  • Learn how to build industry’s leading uses cases eg, Recommendation systems, Speech recognition, commercial grade Image classification and object localization etc…. 
  • Lead ML/DL projects based on TensorFlow implementation

Programme Delivery Methodology:

Face to Face or Online Training

  • Practical/ Lab Exercise
  • eCoaching

Duration:

5 days

Entry Requirement

Basic understanding of IT

Assessment Method

Candidates will need to sit for computerized examination for 1.5 Hours and the various practical exercise.

Learning Materials

There will be a student manual and lab workbook for each participant.

Course Outline:Module 1: Machine Learning Basics

Introduction to Decision Trees

  • Implement Decision Tree training and prediction
  • Formulate a well-posed learning problem          
  • Integrate multiple facets of practical machine learning in a single system: data pre-processing, learning, regularization and model selection
  • Explain the difference between memorization and generalization
  • Implement and analyze existing learning algorithms, including well-studied methods. for classification, regression, structured prediction, clustering, and representation learning

Module 2: Machine Learning As Optimization

  • Linear Regression
  • Logistic Regression (Probabilistic Learning)
  • Design k-NN Regression and Decision Tree Regression
  • Implement learning for Linear Regression using optimization techniques
  • Describe the formal properties of models and algorithms for learning and explain the practical implications of those results

Module 3: Graphical Models

  • Hidden Markov Models
  • Define the first order Markov assumption
  • Draw a Finite State Machine depicting a first order Markov assumption
  • Bayesian Network
  • Interpret the forward-backward algorithm as a message passing algorithm.
  • Compare and contrast different paradigms for learning.  

Module 4: Reinforcement Learning

  • Reinforcement Learning: Value & Policy Iteration
  • Reinforcement Learning: Q-Learning
  • Explain the relationship between a value function mapping states to expected rewards and a value function mapping state-action pairs to expected rewards
  • Design experiments to evaluate and compare different machine learning techniques
  • on real-world problems

Module 5: Learning Paradigms

  • PCA and Dimensionality Reduction
  • Ensemble Methods, Boosting
  • Contrast the theoretical result for the Weighted Majority Algorithm to that of Perceptron
  • Employ probability, statistics, calculus, linear algebra, and optimization in order to develop new predictive models or learning methods

5 Days

Certification Body