(Click Category to List Courses)

37 - ITC - Information Technology - Miscellaneous

ITC 231 - Artificial Intelligence (AI) Deep Learning

Code Start Date Duration Venue
ITC 231 11 March 2024 5 Days Istanbul Registration Form Link
ITC 231 15 April 2024 5 Days Istanbul Registration Form Link
ITC 231 20 May 2024 5 Days Istanbul Registration Form Link
ITC 231 24 June 2024 5 Days Istanbul Registration Form Link
ITC 231 29 July 2024 5 Days Istanbul Registration Form Link
ITC 231 02 September 2024 5 Days Istanbul Registration Form Link
ITC 231 07 October 2024 5 Days Istanbul Registration Form Link
ITC 231 11 November 2024 5 Days Istanbul Registration Form Link
ITC 231 16 December 2024 5 Days Istanbul Registration Form Link
Please contact us for fees


Course Description

Today, Artificial Intelligence (AI) is a thriving field with many practical applications and active research topics. We look to intelligent software to automate routine labor, understand  speech or images, make diagnoses in medicine and support basic scientific research.

In the early days of artificial intelligence, the field rapidly tackled and solved problems that are intellectually difficult for human beings but relatively straight-forward for computers—problems that can be described by a list of formal, math-ematical rules. The true challenge to artificial intelligence proved to be solving the tasks that are easy for people to perform but hard for people to describe formally—problems that we solve intuitively, that feel automatic, like recognizing spoken words or faces in images.

Course Objectives

  • Understanding Machine Learning with ANN and CNN
  • Handling Image and Video data for Machine Learning
  • Discussing the concept of Deep Learning and Computer vision with examples
  • Introduction and setting up Libraries that support Computer Vision
  • Getting hands on experience on each of the concepts

Who Should Attend?

  • Data Scientists
  • Data Engineers
  • Data Architects

Course Details/Schedule

Day 1

  • Structure of data 
  • Academic definition of data 
  • Perceptual framework 
  • Conceptual framework 
  • Employment of data 
  • Collection 
  • Utilization 
  • Fundamental math of AI 
  • Equations, types, forming, and solving, 
  • Functions, types, forming, and solving, 
  • Derivatives, integrals 
  • Statistics or probabilities 
  • Python for AI 
  • Creating vectors 
  • Plotting vectors 
  • Indexing and slicing vectors 

Day 2

  • Data creation 
  • Data preparation
  • Data import and storage 
  • Data manipulations with pandas library 
  • Data transformations – data wrangling 
  • Data orientation 
  • Exploratory analysis 
  • Missing observations – detection and solutions 
  • Outliers – detection and strategies 
  • Standarization, normalization, binarization 
  • Qualitative data recoding 
  • Modeling 
  • Introduction to AI 
  • Philosophy of AI 
  • AI buzzwords [machine learning, deep learning] 
  • Recommendation system 
  • User- based and item- based collaborative filtering
  • Frequent itemsets algorithm 
  • Market basket analysis 
  • Python essentials 
  • Numpy 
  • Pandas 

Day 3

  • Predictive modeling 
  • Simple linear regression 
  • Multiple linear regression 
  • Model selection 
  • Deep predictive modeling 
  • Logistic regression 
  • Non-linear optimization 
  • Python crafting functions 
  • Utilizing functions 

Day 4

  • Neural Network 
  • ANN Structure with biological neurons and artificial neurons
  • Forward propagation flow of ANN with pictorial representation of ANN 
  • Different types of ANN & their typical usage in different domAIns Different types of transfer or activation functions used in ANN 
  • Multi-class classification 
  • Back propagation algorithm for updating & optimizing weights in ANN 
  • trAIning and convergence, functional approximation with back propagation 
  • Gradient descent: full vs batch vs stochastic gradient descent 
  • Deep NN 
  • CNN architecture & how it works 
  • CNN layers & their functionality 
  • Different variations of CNN 
  • Data augmentation 
  • Batch normalization 
  • Introduction to OpenCV & image operations 
  • Complete life-cylce of developing a computer vision model 
  • RNN conceptual review 
  • Python use of tensor flow 
  • Use of Keras 
  • Use of open platforms 

Day 5

  • Comprehension 
  • Hands on trAIning to build, trAIn & use a Computer Vision Model from scratch. 
  • Understanding and using pre-trAIned Computer Vision Models 
  • Keras, Tensor Flow, DLib are preferred libraries for this section 
  • Workshop 
  • Object detection (e.g. Person or Face Detection) 
  • Object classification (e.g. YOLO) 
  • Object recognition (e.g. Face Recognition, FaceNet Model) 
  • Object tracking (Person Tracking)