Admission requirements
Elementary calculus and linear algebra; basics of probability theory and statistics. Fluency in Python; basic commands of Linux.
Description
The course provides an introduction to key concepts and algorithms for neural networks, with strong emphasis on Deep Learning and its applications. It covers the following topics:
Part One: Classical Neural Networks
Basics of statistical pattern recognition
Linear models: Perceptron, Logistic Regression, Support Vector Machines
Multi-layer Perceptron and Backpropagation
Part Two: DeepLearningConvolutional Networks
Recurrent Neural Networks, LSTM and GRU Networks
Reinforcement Learning, DNQ learning
Autoencoders
Restricted Boltzmann Machines
Algorithms for training Deep Networks: SGD, Initialization, Batch Normalization, Dropout
Software and hardware for Deep Learning
Moreover, several state-of-the-art applications of Deep Learning to image recognition, computer vision, language modeling, game playing programs, will be discussed. The course consists of weekly lectures, a few programming assignments (in Python) and the final written exam.
Course objectives
TThe objective of this course are:
to provide a general introduction to the field of deep neural networks and their applications
to develop practical skills for designing and training neural networks for tasks like image classification, speech recognition, forecasting, game playing
to learn some popular tools for training deep architectures: Theano, TensorFlow and Keras
Timetable
The most recent timetable can be found at the students' website
Mode of instruction
Lectures
Computer Lab
Practical Assignments
Assessment method
The final grade will be the weighted average of grades for:
programming assignments (60%)
written exam (40%
Blackboard
See this Blackboard
Reading list
Deep Learning, by Yoshua Bengio, Ian Goodfellow, Aaron Courville (available from http://www.deeplearningbook.org/)
Registration
- You have to sign up for courses and exams (including retakes) in uSis. Check this link for information about how to register for courses.
Contact information
Lecturer: dr. Wojtek Kowalczyk