Profile of TAs

To help you decide with whom you should book a help session, here is a list of the specific expertise our TAs have:

Sofia BrooméLinks to an external site.

Brief Bio: PhD student at RPL working on detecting pain expressions in horses from video data and analysis of video data. 

Deep learning software packages:

  • Tensorflow and Pytorch
  • Experience with both pytorch lightning and ignite
  • Keras

Deep learning methodologies, architectures and application fields:

  • Anything that can model time dependencies in vision: convolutional LSTMs, 3D convolutions, CNNs with RNNs stacked on them, etc.
  • Interpretability for deep video models
  • Multi-view self-supervision (novel view synthesis)
  • Some experience with segmentation
  • Some experience with optical flow
  • Some experience with representation learning
  • Interested in deep learning theory and explainability in general
  • Pose estimation

 

Sebastian Gerard

Brief Bio: PhD student at RPL working on self-supervised learning on satellite images

Deep learning software packages:

  • Pytorch
  • Pytorch Lightning
  • wandb

Deep learning methodologies, architectures and application fields:

  • Self-supervised learning for images
  • Segmentation
  • Satellite images

Yiping Xie

Brief Bio: PhD student in RPL and WASP, working on learning the representations of underwater perception for navigation. 

Deep learning software packages:

  • PyTorch

Deep learning methodologies, architectures and application fields:

  • Generally discriminative models and generative models (VAEs, GANs)
  • Computer Visions applications: depth estimation and etc.
  • Computer Graphics: differentiable rendering, neural representation
  • Sidescan Sonar images

Sebastian Bujwid

Brief Bio: Ph.D. student at RPL. My research is focused on the interaction between natural language processing and computer vision. It involves problems like zero-shot learning from textual descriptions and learning visually grounded language representation.
 
Deep learning software packages:
  • Tensorflow
  • some PyTorch
  • some Jax
Deep learning methodologies, architectures and application fields :
  • Multimodal data: text data, CNN, attention models
  • Generative models (GAN, VAE, image-to-image translation)
  • Computer vision applications: semantic segmentation, depth estimation, etc.

Ruibo Tu

Brief Bio: PhD student at RPL, working on causal discovery and machine learning. 

Deep learning software packages: JAX

Deep learning and causality : Interested in the (causal) representation learning and graph neural networks

 

Alfredo Reichlin

Brief Bio: PhD student at RPL working mainly on Imitation Learning, Offline Reinforcement Learning and Meta Learning for robotic manipulation

Deep learning software packages:

  • pytorch

Deep learning methodologies, architectures and application fields:

  • representation learning from images
  • few-shot adaptation
  • mostly CNN
  • some Graph Neural Networks
  • some generative models (VAEs, GANs)

 

Heng Fang

Brief Bio: Ph.D. student at RPL working on change detection and uncertainty estimation on satellite images

Deep learning software packages:

  • Pytorch

Deep learning methodologies, architectures, and application fields:

  • Computer vision applications in satellite imagery and biomedical scenarios
  • Segmentation, change detection, and uncertainty estimation

I was a student of this course in 2019, feel free to contact me if you have any proposal ideas for the projects.

 

Lennart Alexander Van der Goten

Brief Bio: Third year PhD student at CST (SciLifeLab) working on domain adaptation & anonymization on biomedical data (CT, MRI etc.) 

Deep learning software packages:

  • PyTorch
  • TensorFlow

Deep learning methodologies, architectures and application fields:

  • Generative Adversarial Networks
  • Variational Autoencoders
  • Large-Scale & Distributed Deep Learning
  • DL on volumetric data

 

Moein Sorkhei

Brief Bio: Ph.D. student at SciLifeLab working on transfer learning for biomedical image analysis

Deep learning software packages:

  • PyTorch

Deep learning methodologies, architectures, and application fields:

  • Transfer learning for biomedical image analysis
  • Normalizing flows (worked on this long time ago)

 

Matteo Gamba

Brief Bio: Ph.D student at RPL, working on characterizing the complexity of ReLU networks trained for image classification, by studying their geometry.

Deep learning software packages:

  • PyTorch
  • Jax

Deep learning methodologies, architectures, and application fields:

  • Deep learning theory
  • Interesting empirical phenomena in deep learning
  • Empirical estimation of the geometry of data and neural networks
  • Large-scale and distributed deep learning

Li Ling

Brief Bio: PhD student in RPL, working on sonar-based perception for underwater navigation. 

Deep learning software packages:

  • PyTorch

Deep learning methodologies, architectures and application fields:

  • Keypoint detection, description and matching for images
  • Sidescan Sonar images
  • Interested in contrastive representation learning for images