Tech Talent

Development Support

Data Science & AI
Software Development
Computer Science
Data Science & AI
Software Development
Computer science

Machine Learning – Beginner Level

Machine Learning is an important field of Artificial Intelligence by giving the machine the power to improve its performance by consuming more and more data. In this course, the students will learn the concept of machine learning, especially, supervised learning, and apply various machine learning algorithms in practical problems.

Difficulty

Learning outcomes

  • Improved programming skill.
  • General understanding of Machine Learning and its applications.
  • Ability to recognize different types of machine learning problems
  • Ability to apply some well-known algorithms to solve machine learning problems

Requirements

  • Python programming

Upcoming Courses/Workshops

Group name Start date Session duration Number of sessions Standard price
Machine Learning Beginner Level (Group 3) Jun 18 (Thu) 18:00-20:00 2h 12 sessions (weekly) 84,000 JPY Register
Machine Learning Beginner Level (Group 2) Jun 17 (Wed) 18:00-20:00 2h 12 sessions (weekly) 84,000 JPY Register
Machine Learning Beginner Level (Group 1) Jun 16 (Tue) 18:00-20:00 2h 12 sessions (weekly) 84,000 JPY Register
Register for a FREE Trial Class Register for a 1-on-1 class Course for companies

FEATURED MENTOR

Nghia Truong

Head of AI Product Development
  • Machine Learning consultant and mentor at Tokyo Techies
  • 6+ years of experience working at software service development companies in Japan.
  • 3rd place Vietnam National Olympiad in Informatics 2011
  • Rank 27 at ACM/ICPC Asia Regional contest 2012
  • Champion at multiple Hackathons in Japan and Vietnam
Lession 1

a. Introduction to Machine Learning

  1. Definition, case studies
  2. Types of ML problem

b. Tools for ML

  1. Numpy
  2. Sklearn
  3. Keras and Tensorflow

c. Practice exercises: numpy

Lesson 2

a. Regression problem

  1. Definition, case studies
  2. Problem formulation: Linear regression

b. Metrics

  1. Mean squared error

c. Algorithms

  1. Least square method
  2. Gradient Descent (mention only)

d. Practice exercise

Lesson 3 & 4

a. Classification problem

  1. Definition, case studies
  2. Problem formulation: Binary classification

b. Metrics

  1. Cross entropy loss

c. Algorithms

  1. Logistic Regression
  2. Decision Tree

d. Practice exercises

Lesson 5

a. Data encoding for ML

  1. Ordinal
  2. One-hot

b. Practice exercises

Lesson 6

Mini project:

a. Introduction to Kaggle

b. Titanic: Machine Learning from Disaster

Lesson 7

a.Support Vector Machine

b. Practice exercise

Lesson 8

a. K-Nearest Neighbors

b. Practice exercises

Lesson 9 & 10

a. Neural Network

b. Practice exercises

Lesson 11

a. Unsupervised learning

b. K-mean clustering

c. Practice exercises

Lesson 12

Completion project:

a. A different Kaggle competition

b. -or- student’s specific project

Recommended after this course

Machine Learning – Intermediate Level

Gain Intermediate-Advanced programming skills with Python and hands-on experience in how to build and train Machine Learning models with real datasets.

Difficulty
Read More
KEY STATION OFFICE, New Shinbashi Building 903, Shinbashi 2-16-1, Minato, Tokyo 1050004
03 3527 9993
info@tokyotechies.com
© 2020 Tokyo Techies. All rights reserved.