Artificial Neural Networks: from the Ground Up
Beschrijving
Since their earliest conception in the 1940s, artificial neural networks have been alternatively regarded as extremely promising machine learning models, capable of learning anything, and as glorified linear combinations, unable to achieve relevant results in practice.
However, along the last decade, the availability of general-purpose GPU architectures and large quantities of data has enabled the rise of deep neural networks, which have attained state-of-the-art performance in many applications, from image classification to text translation. This has given rise to a whole new field of research, ranging from generative models to adversarial attacks (and defenses against them).
This course is intended as a first contact with artificial neural networks, followed by an overview of the different architectures that are currently available.
This course is part of a larger course series in Data Analysis consisting of 19 individual modules. Find more information and enroll for this module via www.ipvw-ices.ugent.be
Programma
- Introduction to neurons and neural networks
- Training with backpropagation
- Challenges and solutions to train deep neural networks
- Convolutional networks
- Adversarial examples
- Generative models: Autoregressive models, Autoencoders, Variational autoencoders (VAE), Generative adversarial networks (GAN)
- Transformers and BERT
- Recurrent neural networks
The practical sessions use the Python library TensorFlow to implement some of the models discussed in the course, with particular emphasis on how to adapt the networks to the characteristics of a specific problem.
Schrijf je hier in voor lessen uit deze cursus
Artificial Neural Networks: from the Ground Up
- Type of course: This is an on campus course.
- Dates & times: April 21 and 28, May 5, 12 and 19, 2022, from 5.30 pm to 9 pm
- Venue: UGent, Faculty of Sciences, Campus Sterre, Krijgslaan 281, building S9, 9000 Gent
- Target audience: This course is aimed at professionals and investigators from diverse areas who want to learn how to apply neural networks on diverse problems, or who want to learn about the possibilities, applicability, and variants of neural networks.
- Exam/certificate: Participants who attend all classes receive a certificate of attendance via e-mail at the end of the course. Additionally, participants can, if they wish, take part in an exam. Upon succeeding in this test a certificate from Ghent University will be issued. The exam consists of a take home project assignment. Students are required to write a report by a set deadline.
- Course prerequisites: Basic knowledge of the Python programming language is required equivalent to Module 4 - Getting Started with Python for Data Scientists of this year's program.o
- Funding: => Our academy is recognised as a service provider for the 'KMO-portefeuille'. In this way small and middle sized businesses located in the Flanders region can save up to 30% on the registration fee for our courses. You can request this subsidy via www.kmo-portefeuille.be up until 14 calender days after the course has started. => UGent PhD students can apply for a full refund from their Doctoral School.
- Reduction: => If two or more employees from the same company enrol simultaneously for this course a reduction of 20% on the module price is taken into account starting from the second enrolment => Reduced prices apply to coworkers in governmental institutions, non-profit organisations and higher eduction as well as for students and the unemployed.
- Enrolling for this course is possible via the IPVW-ICES website.