🏠 HOME
Welcome to the Neural Coding Lab. We are an interdisciplinary team of artificial intelligence and cognitive neuroscience researchers at Radboud University, Donders Institute for Brain, Cognition and Behaviour), Nijmegen, the Netherlands. Our research combines neural coding with deep learning to develop models of neural computation in silico with artificial neural networks and in vivo with neuroimaging. tl;dr: ❤️=🤖+🧠.
Thirza has won the annual Donders best poster award with HYPER. 📜🏆🚀
Our paper "Brain2Pix: Fully convolutional naturalistic video reconstruction from brain activity" has been posted at bioRxiv
Our paper "End-to-end neural system identification with neural information flow" has been accepted at PLOS Computational Biology
Our paper "Cortical network responses map onto data-driven features that capture visual semantics of movie fragments" has been published at Scientific Reports 🔗
Our paper "The Indian chefs process" has been published at Uncertainty in Artificial Intelligence 🔗
Our paper "Hyperrealistic neural decoding: Linear reconstruction of face stimuli from fMRI measurements via the GAN latent space" has been posted at bioRxiv 🔗
Our paper "Brain-optimized extraction of complex sound features that drive continuous auditory perception" has been published at PLOS Computational Biology 🔗
Our paper "Explainable 3D convolutional neural networks by learning temporal transformations" has been posted at arXiv 🔗
Our paper "Detecting neural state transitions underlying event segmentation" has been posted at bioRxiv 🔗
Our paper "Guest editorial: Image and video inpainting and denoising" has been published at IEEE Transactions on Pattern Analysis and Machine Intelligence 🔗
Our paper "Modeling, recognizing and explaining apparent personality from videos" has been published at IEEE Transactions on Affective Computing 🔗
We have been granted research funding for three PhD candidates
neuralcoding.nl has gone live 🥳🎈🎉
📛 CONTACT
Dr. Umut Güçlü
Radboud University, Donders Institute for Brain, Cognition and Behaviour
u.guclu@donders.ru.nl
+31243611158
Postbus 9104, 6500 HE, Nijmegen, Netherlands
SP B 00.98, Montessorilaan 3, 6525 HR, Nijmegen, Netherlands
🥼 PEOPLE
Alumni
Katja Seeliger (PhD)
Marleen Voorn (MSc AI & CNS)
Thirza Dado (MSc AI & CNS)
Amanda Wintermans (MSc CNS)
Sven den Hartog (MSc AI)
Lynn Le (MSc Medical Biology)
Lars Bokkers (MSc AI)
Kevin Koschmieder (MSc AI)
Jordy Thielen (MSc AI & CNS)
Collaborators
Prof. Sergio Escalera
Prof. Marcel van Gerven
Prof. Isabelle Guyon
Prof. Rob van Lier
Prof. Pieter Roelfsema
Prof. Richard van Wezel
Dr. Luca Ambrogioni
Dr. Linda Geerligs
Dr. Yağmur Güçlütürk
Dr. Pim Haselager
Dr. Jan Mathijs Schoffelen
✏️ PUBLICATIONS
.
📚 TEACHING
SOW-MKI95 Computer Graphics & Computer Vision
Coordinator: Dr. Umut Güçlü
TAs: Lynn Le and Thirza Dado
Time: Spring semester (Periods 3 and 4)
This course will teach you contemporary computer graphics and computer vision from underlying theories to best practices. In weekly theoretical lectures and practical labs, you will study cutting-edge topics such as:
Foundations of depth-buffered triangle rasterization, the rendering pipeline, advanced lighting and global illumination, visual effects and overlays (optional reference 📕)Pseudorandom numbers, Lindenmayer systems, landscape generation, dungeons and maze generation, shape grammars (optional reference 📕)Generative modeling, deep learning, variational autoencoders, generative adversarial networks (optional reference 📕)
Upon successful completion of this course, you will be able to:
Understand computer graphics topics such as rendering, shaders and procedural content generation as well as implementing them in Unity/C#Understand computer vision topics such as generative modeling, deep learning, variational autoencoders and generative adversarial networks as well as implementing them in Gluon/MxNet/Python
For more information, refer to do the course guide and the course website.
SOW-BKI230A Deep Learning (née Neural Networks)
Coordinator: Dr. Umut Güçlü
TA: Burcu Küçükoğlu and Dora Gözükara
Time: Spring semester (Periods 3 and 4)
This course will teach you all about deep learning from the AI winters of the past to the deep learning revolution of the present. In weekly theoretical lectures and practical labs, you will study several topics from the open source 📕 Dive into Deep Learning such as:
Linear neural networks and multilayer perceptronsDeep learning computation, (modern) convolutional neural networks, (modern) recurrent neural networks and attention mechanismsOptimization algorithms and computational performance
Upon successful completion of this course, you will be able to understand the following and implement them in Gluon/MxNet/Python:
Basics and preliminaries of deep learningModern deep learning techniquesScalability, efficiency and applications of deep learning
For more information, refer to do the course guide and the course website.
In addition to our two courses, we give regular (guest) lectures/labs in the following courses:
SOW-BKI114 Human-Computer Interaction (UG, LL, TD)SOW-MKI46 Brain Reading and Writing (UG, DO, DG)SOW-MKI49 Neural Information Processing Systems (UG, LL)SOW-MKI66 Advanced Academic & Professional Skills (UG)SOW-DGCN01 Trends in Cognitive Neuroscience (UG)