LUMLIS - The Lisbon ELLIS Unit | People | Structure | News | Events | Corporate Supporters | Contact

Lisbon Unit for Learning and Intelligent Systems

We are pleased to announce the creation of the Lisbon Unit for Learning and Intelligent Systems (LUMLIS), a unit of the European Laboratory for Learning and Intelligent Systems (ELLIS), hosted at the Instituto Superior Técnico (IST) of the University of Lisbon (UL).

The LUMLIS Reading Group @ INESC-ID

This Machine Learning Reading Group meets regularly to discuss research topics on different sub-fields of Machine Learning.
INESC-ID

Reading Group Schedules

Summer Term 2020 Tuesdays at 1:00 PM
Date Presenter Topic
Feb 4 Alexandre Borges Deep Residual Learning - [paper]
Feb 11 João Monteiro Densely Connected Convolutional Networks - [paper]
Mar 3 Tomás Oliveira EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks - [paper]
Apr 7 Miguel Freire Playing Atari with Deep Reinforcement Learning - [paper]
Apr 21 Arlindo Oliveira ImageNet Classification with Deep Convolutional Meural Networks - [paper]
May 5 Luís Borges Passage Re-ranking with BERT - [paper]
May 19 Rita Ramos Show, Attend and Tell: Neural Image Caption Generation with Visual Attention - [paper]
Jun 2 Arlindo Oliveira Generative Adversarial Nets - [paper]
Jun 16 Miguel Monteiro Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty - [paper]
Jul 7 Dinis Rodrigues Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks - [paper]


Winter Term 2020 - 2021 Tuesdays at 1:00 PM
Date Presenter Topic
Sep 8 Inês Filipe Very Deep Convolutional Networks for Large-Scale Image Recognition - [paper]
Sep 22 André Godinho Recipes for building an open-domain chatbot - [paper]
Sep 29 André Cavalheiro Recurrent Neural Networks - [book chapter]
Oct 6 Rita Ramos GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks - [paper]
Oct 13 Dinis Rodrigues Automated Stenosis Detection and Classification in X-ray Angiography Using Deep Neural Network - [paper]
Oct 20 João Moura Language Models are Few-Shot Learners - [paper]
Oct 27 João Monteiro Self-training with Noisy Student improves ImageNet classification - [paper]
Nov 3 João Rico Semi-Supervised Classification with Graph Convolutional Networks - [paper]
Nov 10 Pedro Stralen Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey - [paper]
Nov 17 João Cardoso A Simple Framework for Contrastive Learning of Visual Representations - [paper]
Nov 24 Rafael Pedro Rotate to Attend: Convolutional Triplet Attention Module - [paper]
Dec 15 Tiago Mesquita Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer - [paper]
Dec 22 Mário Cardoso STConvS2S: Spatiotemporal Convolutional Sequence to Sequence Network for Weather Forecasting - [paper]
Jan 5 Susana Vinga Structured sparsity regularization for analyzing high-dimensional omics data - [paper]
Jan 12 Manuel Coimbra Modeling Relational Data with Graph Convolutional Networks - [paper]
Jan 19 Mário Figueiredo The free-energy principle a unified brain theory - [paper]
Jan 26 Tiago Oliveira Informed Machine Learning – A Taxonomy and Survey of Integrating Knowledge into Learning Systems - [paper]
Feb 2 Daniel Oliveira Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering - [paper]
Feb 9 João Cardoso COVID-19 Deterioration Prediction via Self-Supervised Representation Learning and Multi-Image Prediction - [paper]
Feb 16 Mário Cardoso RepVGG: Making VGG-style ConvNets Great Again - [paper]
Feb 23 João Barata LambdaNetworks: Modeling long-range Interactions without Attention - [paper]


Summer Term 2021 Tuesdays at 1:00 PM
Date Presenter Topic
Mar 2 Rita Ramos CPTR: Full Transformer Network for Image Captioning - [paper]
Mar 16 João Lourenço Silva SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation - [paper]
Mar 30 Beatriz Vieira Generative Pretraining from Pixels - [paper]
Apr 13 Arlindo Oliveira The Consciousness Prior - [paper]
Apr 27 Alexandre Borges Combining Off and On-Policy Training in Model-Based Reinforcement Learning - [paper]
May 11 Nuno Infante CheXpert++: Approximating the CheXpert labeler for Speed, Differentiability, and Probabilistic Output - [paper]
May 25 Rita Ramos Unifying Vision-and-Language Tasks via Text Generation - [paper]
June 22 João Lourenço Silva Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation - [paper]
June 29 Arlindo Oliveira Modeling the geospatial evolution of COVID-19 using spatio-temporal convolutional sequence-to-sequence neural networks - [paper]


Winter Term 2021 - 2022 Tuesdays at 1:00 PM
Date Presenter Topic
Sep 21 Miguel Freire CutPaste: Self-Supervised Learning for Anomaly Detection and Localization - [paper]
Sep 28 To be announced To be announced - [paper]