Deep Learning is a subset of Machine Learning which is completely based on artificial neural networks. As neural networks are designed to mimic the human brain, deep learning is likewise a human brain mimic. These neural networks are made up of a simple mathematical function that can be stacked on top of each other and arranged in the form of layers, giving them a sense of depth, hence the term Deep Learning.
5 ECTS (or course certificate)
With credits: 04.09.2024 Without credits: To be announced
Bachelor
With credits: 15.08.2024 Without credits: To be announced
Online
With credits: Kr. 9.500 NOK + semester fee and literature Without credits: 3500 NOK+literature
Learn more about the power of neural networks and get a better understanding of artificial with our Deep Learning course.
Course content
![Kvinne som tenker](https://training.uis.no/sites/default/files/2023-11/IKKE%20BRUK%21%20KVINNE%20.jpg)
Deep Learning has a plethora of applications in almost every field such as health care, finance, and image recognition. It can be used to solve any pattern recognition problem and without human intervention. There are several popular and widely used deep learning frameworks that help to build neural network models. Some of the common ones are Tensorflow, Keras, PyTorch, and DL4J.
In this course, in addition to getting a solid understanding of deep learning, you will get hands-on experience by solving practical, real-life tasks using state-of-the-art techniques and software frameworks from machine learning, and deep learning. The concepts covered in this course provide relevant theoretical and hands-on programming knowledge.
This course covers the following topics:
- Introduction to Deep Learning (Deep Learning Fundamentals, AI vs. Machine Learning vs. Deep Learning - Relationship Overview)
- Artificial Neural Networks (Perceptrons, Intro to Artificial Neural Networks, Layers in Artificial Neural Networks, Activation Functions in Artificial Neural Networks, Loss Functions in Artificial Neural Networks, Training Artificial Neural Networks, Batch Size & Epochs in Artificial Neural Networks, Optimization Algorithms in Artificial Neural Networks, Learning Rates in Artificial Neural Networks, Backpropagation Intuition - Neural Network Training, Bias in Artificial Neural Networks) .
- Additional Fundamental topics (Datasets for Deep Learning - Training, Validation, & Test Sets, Overfitting- Artificial Neural Networks, Underfitting- Artificial Neural Networks, Tensor flow, and Keras, Multi-Layer Perceptron (MLP), Classification with the Tensor flow and MLP, Regression with the Tensor flow and MLP)
- Convolutional Neural Networks (CNNs) (What are CNNs? Visualizing convolutional filters, Zero padding, Max pooling)
- Recurrent Neural Networks (RNN) (What are RNNs? Architecture, Applications of RNNs)
- LSTM (General structure of LSTM neural network, RNN neural network, and long-term dependence, LSTM neural network and long-term dependence, LSTM network architecture)
Learning outcome
After taking this course, you will:
- have a firm understanding of the most fundamentals of modern neural networks and their practical use
- Identify the deep learning algorithms which are more appropriate for various types of learning tasks in various domains.
- Implement deep learning algorithms and solve real-world problems.
Teaching
- Teaching language: English
- Weekly lectures published as videos
- One hands-on use-case based assignments will be assigned to the students
- Three voluntary live sessions will be conducted to discuss the solutions for each assignment
- Course Starts: Monday, September 04 with an online kick-off meeting
- Assignment #1
- Start: September 25
- Live discussion on October 2
- End: October 13
- Start: September 25
- Assignment #2
- Start: October 16
- Live discussion on October 23
- End: November 3
- Start: October 16
- Course End: November 10
Examination
- The assignment is mandatory - approved / not approved
- Submissions should provide coding solutions to the respective problems with proper documentation
- Individual home exam. [Grade: A-F]
- Exam date: 13.11.2024 (duration: one week)
Admission requirements
- Foreign applicants must document education and English skills in accordance with NOKUT's regulations.
Admission
- We practice the first-come, first-served principle when registering this course, as long as you qualify for admission based on the admission requirements and the prerequisite knowledge
Required prerequisite knowledge
- None
Recommended prerequisite knowledge
- E-DAT120 Introduction to Programming
Syllabus
- The syllabus are the lecture slides with references.
The course will be set up as long as there is a sufficient amount of applicants
Lecturer
Department of Electrical Engineering and Computer Science
In this course, in addition to getting a solid understanding of deep learning, you will get hands-on experience by solving practical, real-life tasks using state-of-the-art techniques and software frameworks from machine learning, and deep learning. The concepts covered in this course provide relevant theoretical and hands-on programming knowledge. This course covers the following topics: • Introduction to Deep Learning (Deep Learning Fundamentals, AI vs. Machine Learning vs. Deep Learning - Relationship Overview) • Artificial Neural Networks (Perceptrons, Intro to Artificial Neural Networks, Layers in Artificial Neural Networks, Activation Functions in Artificial Neural Networks, Loss Functions in Artificial Neural Networks, Training Artificial Neural Networks, Batch Size & Epochs in Artificial Neural Networks, Optimization Algorithms in Artificial Neural Networks, Learning Rates in Artificial Neural Networks, Backpropagation Intuition - Neural Network Training, Bias in Artificial Neural Networks) .
• Additional Fundamental topics (Datasets for Deep Learning - Training, Validation, & Test Sets, Overfitting- Artificial Neural Networks, Underfitting- Artificial Neural Networks, Tensor flow, and Keras, Multi-Layer Perceptron (MLP), Classification with the Tensor flow and MLP, Regression with the Tensor flow and MLP)
• Convolutional Neural Networks (CNNs) (What are CNNs? Visualizing convolutional filters, Zero padding, Max pooling)
• Recurrent Neural Networks (RNN) (What are RNNs? Architecture, Applications of RNNs)
• LSTM (General structure of LSTM neural network, RNN neural network, and long-term dependence, LSTM neural network and long-term dependence, LSTM network architecture)