
Hands-on Machine Learning and Artificial Intelligence
Jump into the fascinating world of artificial intelligence
24 hours
20
Instructor-led, hands-on exercises
Hebrew
Bring your own (installation instructions will be sent prior to course start)
Included
What do cancer detection, sentiment analysis, image recognition, machine translation and playing atari games have in common? These are all complex real-world tasks, and the goal of artificial intelligence (AI) is to tackle these with powerful mathematical and programmatic tools. In this course, you will learn the foundational principles that enables machines to make autonomous decisions and practice implementing some of these systems. The main goal of the course is to equip you with the tools to tackle new AI problems you might encounter in your field of interest.
Objectives
Key elements you will encounter:
- The concept of loss functions and gradient descent optimizer
- Build machine learning models based on domain knowledge
- Visualize and explore datasets using python
- Extract informative features and transform them to fit into specific algorithm
- Implement NLP and text analysis tools to analyze sentiment of tweets
- Get familiar with the theory and implementations of several learning algorithms: ANN, XGB, Random Forest, Logistic Regression
Prerequisites
We recommend that attendees of this course have the following prerequisites:
- Academic skill level of calculus, linear algebra, statistics
- Basic programming experience
- Python, Analytical approach - Advantage
Syllabus
- Basic concepts in machine learning
- Linear regression
- Classification task
- Dependent and explanatory variables
- Feature extraction
- Classification with decision trees
- Feature importance and automatic feature selection by information gain
- Overfitting and regularization in trees
- Tree ensemble
- Backpropagation - implement a single neuron
- Neural nets. playground
- Activation functions
- Image recognition using DNN, CNN
- Imitation learning
- Deep Q learning
- OpenAI Gym - learning to play games
- Policy iterations, value iterations