 Nie jesteś zalogowany | zaloguj się |
| Nie jesteś zalogowany | zaloguj się |
2021-03-25, godz. 12:15, meet.google.com/yew-oubf-ngi
Bartłomiej Polaczyk
Loss landscape of deep neural networks
Finding the global minimum of a general non-convex function is in general an NP-complete problem. The optimization objective of deep neural networks (DNN) is not only non-convex but even non-smooth in case of ReLU activation function. Yet, practice suggests that even simple first-order methods such ...
2021-03-18, godz. 12:15, meet.google.com/yew-oubf-ngi
Piotr Tempczyk
LIDL: Local Intrinsic Dimension estimation using Likelihood
We investigate the problem of local intrinsic dimension (LID)estimation. LID of the data is the minimal number of coordinates which are necessary to describe the data point and its neighborhood without significant information loss. Existing methods for LID estimation do not scale well...
2021-03-04, godz. 12:15, meet.google.com/yew-oubf-ngi
Kajetan Janiak
Modelling rigid body dynamics with physics-informed neural networks
Functions describing physical systems of rigid bodies lie in a low-dimensional subspace of functions that neural networks can represent. If we could construct a NN architecture, that for any set of parameters yields dynamics of some rigid bodies’ system, then we could improve sample efficiency...
2021-02-04, godz. 12:15, meet.google.com/yew-oubf-ngi
Jacek Cyranka
Safety (Constrained) Reinforcement Learning
This is a "reading group" type of seminar - expect less polished presentation, more of a learning effort for the interested participants. ...
2020-11-26, godz. 12:15, google meet (meet.google.com/yew-oubf-ngi)
Piotr Januszewski
Decision making in uncertainty: Introduction to Multi-Armed Bandits algorithms
There are many reasons to care about bandit problems. Decision-making with uncertainty is a challenge we all face, and bandits provide a simple model of this dilemma we can study. Bandit problems have practical applications like configuring web interfaces, where applications include news recommen...
2020-11-12, godz. 12:15, meet.google.com/yew-oubf-ngi
Tomasz Danel (Jagiellonian University)
Machine Learning in Computer-Aided Drug Design
Drug discovery is a long and expensive process. Currently, pharmaceutical companies begin to acknowledge the potential of machine learning methods. These methods enable the effective exploration of the chemical space and the rapid identification of promising chemical compounds. During the present...
2020-10-29, godz. 12:15, google meet (meet.google.com/yew-oubf-ngi)
Michał Garmulewicz
Towards structured world models for control
In recent years model-based RL has broadly lived up to its promise and has kept bringing outstanding benchmark performance, especially in the limited data regime. Secondly, there is a growing interest in using structural priors to improve world models, making them less data-hungry, mor...
