Deep learning with Python

This is an introductory course where you will learn how to train high-dimensional non-linear models, represented by deep artificial neural networks (ANN), using few lines of Python code. Deep learning is an umbrella term for methods using deep nets, i.e., ANNs that consist of several consecutive layers of artificial neurons. The course gives you a brief overview of gradient descent which is the most widely used algorithm for tuning the weights of deep nets.
Image for course subject

Schedule:

Teaching time:

Self-paced

Location:

Online

Topic:

Information and communications technology

Form of learning:

Online

Provider:

Aalto University, FITech

Level:

Intermediate

Credits:

2 By Aalto University (ECTS)

Fee:

Free of charge

Target group and prerequisites

High-school math (functions, derivatives, vectors). Basic Python programming (variables, functions, loops). The course Machine Learning with Python.

Course description

This course is an introduction to deep learning.

This is an introductory course where you will learn how to train high-dimensional non-linear models, represented by deep artificial neural networks (ANN), using few lines of Python code. Deep learning is an umbrella term for methods using deep nets, i.e., ANNs that consist of several consecutive layers of artificial neurons. The course gives you a brief overview of gradient descent which is the most widely used algorithm for tuning the weights of deep nets. You will learn some powerful tricks that allow tuning billions of ANN weights using only hundreds of training examples. Some of the most successful deep learning methods are enabled by few clever regularization techniques, such as data augmentation and transfer learning, to avoid overfitting.

After successfully completing the course, the student

  • understands how ANNs can be used for learning and evaluating high-dimensional non-linear models.
  • understands the basic principle of gradient descent.
  • is able to build, and train ANNs using the Python package Keras.
  • is able to diagnose the learning process by comparing training with validation loss.
  • is able to use data augmentation to synthetically enlarge the training set.
  • is able to implement transfer learning by fine-tuning a pre-trained deep net.

The grading is based on coding assignments and student projects.

  • Updated:
Share
URL copied!

You might be interested in these

Fundamental courses

Image for course subject

Machine learning transforms our lives

Information and communications technology

Location:
Online
Level:
Beginner
Image for course subject

Informaatioteknologian perusteet

Information and communications technology

Location:
Espoo
Level:
Beginner
Image for course subject

Cybersecurity

Information and communications technology

Location:
Online
Espoo
Level:
Beginner
Image for course subject

Introduction to web development and programming

Information and communications technology

Location:
Online
Level:
Beginner
Image for course subject

Introduction to digital transformation

Information and communications technology

Location:
Online
Level:
Beginner
Image for course subject

Digital ethics and sustainability

Information and communications technology

Location:
Online
Level:
Beginner

Intermediate courses

Image for course subject

Digital Platform Economy

Information and communications technology

Location:
Online
Level:
Intermediate
Image for course subject

Tietokannat

Information and communications technology

Location:
Espoo
Level:
Intermediate
Image for course subject

Tietokoneverkot

Information and communications technology

Location:
Espoo
Online
Level:
Intermediate
Image for course subject

Tietoliikenteen siirtomenetelm├Ąt

Information and communications technology

Location:
Espoo
Level:
Intermediate
Image for course subject

Capstone: Information Systems Development

Information and communications technology

Location:
Espoo
Level:
Intermediate
Image for course subject

Management Information Systems

Information and communications technology

Location:
Espoo
Level:
Intermediate

Advanced courses

Image for course subject

Speech Recognition

Information and communications technology

Location:
Espoo
Level:
Advanced
Image for course subject

ICT Enabled Service Business and Innovation

Information and communications technology

Location:
Online
Espoo
Level:
Advanced
Image for course subject

Value network design for internet services

Information and communications technology

Location:
Espoo
Level:
Advanced
Image for course subject

SDN fundamentals & techniques

Information and communications technology

Location:
Espoo
Level:
Advanced
Image for course subject

Performance analysis

Information and communications technology

Location:
Espoo
Level:
Advanced
Image for course subject

Machine type communications for internet of things

Information and communications technology

Location:
Espoo
Level:
Advanced