View All Pages

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 Broomé

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:

  • Mainly Tensorflow (including tfrecords)
  • But also some Pytorch
  • 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
  • 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

 

Chris Sprague

Brief Bio: PhD student at RPL and SMaRC Links to an external site., working on learning optimal information gathering behaviours in autonomous underwater vehicles.

Deep learning software packages:

  • JAX
  • Pytorch and GPyTorch
  • Some experience with Tensorflow and GPflow

Deep learning methodologies, architectures and application fields:

  • Interested in optimal control and planning using ML.
  • Mainly using physics-informed learning.
  • Experience with PointNet, Lagrangian neural networks, Bayesian optimisation.

 

Matteo Gamba

Breef bio: PhD student at RPL, working on studying the properties of the functions learned by deep networks for image classification

Deep learning software packages:

  • Pytorch!

Deep learning methodologies, architectures and application fields:

  • I am working on the general problem of identifying the inductive bias of ConvNets by studying hyperplane  arrangements and activation regions of trained networks
  • Anything concerning complexity measures (in the statistical learning sense) and their relationship to implicit regularization/capacity control at play during training
  • Interested in deep learning theory and interpretability in general

Lennart Alexander Van der Goten

Brief Bio: First 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

 

Erik Englesson

Brief Bio: PhD student at RPL, investigating efficient uncertainty estimation for image classification. 

Deep learning software packages:

  • Pytorch

Deep learning methodologies, architectures and application fields :

  • Uncertainty Estimation: calibration, out-of-distribution detection, adversarial examples
  • Soft Labels: knowledge distillation, mixup, label smoothing, entropy regularization etc
  • Meta: Recently, I have also been looking into meta-learning approaches

Federico Baldassarre (Links to an external site.)

Brief Bio: PhD student in Deep Learning at RPL since 2018. Before this, I was a student in the Machine Learning master at KTH, during which I've also spent 3 months at a startup in Kuala Lumpur and 6 months at Zalando Research in Berlin. I've been a TA for DD2380 Artificial Intelligence, DD2424 Deep Learning in Data Science, DD2412 Deep Learning Advanced, and DD2423 Image Analysis and Computer Vision.
KTH email: fedbal
 
Deep learning software packages:
  • PyTorch, by far my favorite
  • Keras/TensorFlow, I can probably answer high-level questions
  • Jax, I tried it and I'll wait for it to become more mature
Deep learning methodologies, architectures and application fields :
  • I like all aspects of computer vision and I do my best to be up to date on all CV topics, like dense detections, action recognition, pose estimation, image generation, relationship detection etc. 
  • My overall PhD project is about explainability and interpreting the predictions of deep neural networks, which involves gradient-based explanation techniques and inductive biases for reasoning
  • I worked with graph networks and transformers, I keep up with the literature on this topic and I've applied them to molecules and proteins, with also the idea of using relational models to improve interpretability.
  • I plan to work on deep fakes in the upcoming months, in particular, deep fake detection in videos

 

Ruibo TuLinks to an external site.

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

I was a student of this course in 2017. If you have questions about

  • understanding the content of lectures,
  • understanding about implementing assignments, 
  • proposal ideas for the project,

Deep learning software packages:

  • Tensorflow: the same level as if you finished the course.

Deep learning and causality :

  • Interested in the causal representation learning and the disentanglement representation learning
  • Appreciate Wasserstein GAN, VAE, and continuous normalizing flow (Neural ODE)

 

Sebastian Bujwid

Contact information: bujwid@kth.se
Brief Bio: PhD student at RPL working on combining language and vision with deep learning.
 
Deep learning software packages:
  • Tensorflow (1.x & 2.x)
  • PyTorch
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.

 

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.

 

Li Ling

Brief bio: First year PhD student at RPL and SMaRC, working with underwater perception and navigation, primarily using sonar data.

Deep learning software packages:

  • PyTorch
  • Deep Graph Library (currently exploring a bit)

Deep learning methodologies, architectures and application fields:

  • Mostly CNNs
  • Keypoint detection and description networks
  • Currently exploring a bit about graph neural networks

 

Yue Liu

Brief Bio: PhD student in CSC/RPL , working on deep learning for breast cancer risk assessment and detection in mammograms 

Deep learning software packages:

  • Tensorflow (1.x/2.x)

Deep learning methodologies, architectures and application fields:

  • CNNs with medical images
  • Some experience with knowledge distillation 
  • Some experience with self-supervised learning