At a Glance

Name: Machine Learning Fundamentals - Week 1
Price: Free CAD
Rating: 4.8 (6 reviews)
Author: abdul_fatir

Develop strong skills in artificial intelligence by mastering fundamental techniques and concepts. Build upon theoretical machine learning through application on real world tasks.

Week 1 Content: Introduction to Machine Learning and Linear Regression

This first workshop covers three main sections: an Introduction to UTMIST and the MLF Program, an Introduction to Machine Learning, and an initial step into ML with Linear Regression.

Introduction to ML Concepts

Machine Learning is defined as the study of data to find its patterns and underlying distribution. The slides contrast ML with Traditional Programming, where traditional programming relies on hand-crafted logic and results in high transparency, while ML derives its patterns from data, has low transparency, and is easier to adapt to large, complex problems.

The presentation also outlines several major fields of ML and their applications:

Computer Vision: Deals with what the computer "sees," used for image classification, object detection (like in self-driving cars), and face recognition.
Natural Language Processing (NLP): Deals with human language, applied in sentiment classification, fraud detection, and text generation (Language Models like ChatGPT).
Reinforcement Learning: Learning through trial and error, relevant for self-driving cars, robots learning to walk, and AI playing games like Chess (e.g., Alpha-Go).
Generative AI: Generating new data, such as image, video, and text generation.

The workshop focuses on the three types of ML methods:

Supervised Learning (MLF Focus): Learning from data with answers (labels).
Unsupervised Learning: Finding patterns in data without answers (no labels).
Reinforcement Learning: Learning through Trial & Error.

They also introduce two main problem types that MLF will focus on: Regression and Classification.

Offered By: IBMSkillsNetwork

Machine Learning Fundamentals - Week 1

At a Glance