Nie jesteś zalogowany | zaloguj się

Wydział Matematyki, Informatyki i Mechaniki Uniwersytetu Warszawskiego

  • Skala szarości
  • Wysoki kontrast
  • Negatyw
  • Podkreślenie linków
  • Reset

Seminarium "Uczenie maszynowe"

Lista referatów

  • 2023-06-01, godz. 12:15,

    Konrad Staniszewski (Uniwersytet Warszawski)

    Retrieval Augmented Language Models

    Large language models store their knowledge in parameters and require costly fine-tuning to update. An interesting alternative is to provide new knowledge in the model's context. However, typical models have relatively short context lengths. In this presentation, I will discuss one of the pote...

  • 2023-05-25, godz. 12:15,

    Mateusz Olko (Uniwersytet Warszawski)

    Causal Machine Learning: Introduction

    Causality has the potential to transform the way we solve a large number of real-world problems. This mathematical theory, introduced by Judea Pearl, has recently paved its way into the deep learning community. In my presentation, I will introduce and explain basic concepts from causality theory and...

  • 2023-05-18, godz. 12:15,

    Dominik Filipiak

    Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding

    We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learning framework. To filter out noisy pseudo-labels, we use confidence thresholding for bounding boxes and mask scoring for...

  • 2023-04-20, godz. 12:15,

    Hubert Baniecki (Uniwersytet Warszawski)

    Segment Anything

    Hubert will talk about a very recent paper that has impressive instance segmentation results. ...

  • 2023-04-13, godz. 12:15,

    Mohammad Saqib (Uniwersytet Warszawski)

    Protein secondary structure assignments using ML

    Researchers seek to understand computer-generated protein models by identifying their structural components. Categorizing amino acid residues as Helix, Strand, or Coil types is the process used for this identification. This categorization can be challenging if certain atoms are missing or only alpha...

  • 2023-03-30, godz. 12:15,

    Michał Zawalski

    Reinforcement learning with latent representations

     When working with complex high-dimensional objects, it is usually beneficial to translate them into compact low-dimensional forms. In my talk, I will discuss some successful approaches that learn meaningful representations for efficient reinforcement learning.   ...

  • 2023-01-19, godz. 12:15, 5050

    Michal Nauman (Uniwersytet Warszawski)

    All-Action Policy Gradients

    In this talk, we will discuss policy gradients with many action samples. We will investigate decompositions of policy gradient variance, as well as measure the variance reduction effect stemming form increasing the number of state and action samples used in estimation. Finally, we will compare vario...

  • 2022-12-08, godz. 12:15,

    Spyros Mouselinos (Uniwersytet Warszawski)

    A Simple, Yet Effective Approach to Finding Biases in Code Generation

    Recently, scores of high-performing code generation systems have surfaced. As has become a popular choice in many domains, code generation is often approached using large language models as a core, trained under the masked or causal language modeling schema. This work shows that current code gene...

  • 2022-11-03, godz. 12:15, 5050

    Piotr Tempczyk (Uniwersytet Warszawski)

    One Simple Trick to Fix Your Bayesian Neural Network

    One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to fit with MFVI. We provide a theoretical justification for this phenome...

  • 2022-10-27, godz. 13:15,

    Patrik Reizinger (University of Tübingen)

    Embrace the Gap: VAEs Perform Independent Mechanism Analysis

    Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidence lower bound (ELBO), at the expense of a gap to the exact (log-)marginal likelihood. While VAEs are commonly used for r...