 Nie jesteś zalogowany | zaloguj się |
| Nie jesteś zalogowany | zaloguj się |
2022-03-17, godz. 12:15, meet.google.com/ooi-zxye-dxa
Spyros Mouselinos (University of Warsaw)
Measuring CLEVRness: Black-box Testing of Visual Reasoning Models
How can we measure the reasoning capabilities of intelligence systems? Visual question answering provides a convenient framework for testing the model's abilities by interrogating the model through questions about the scene. However, despite scores of various visual QA datasets and architectures...
2022-03-03, godz. 12:15, meet.google.com/ooi-zxye-dxa
Michał Zawalski (Uniwerystet Warszawski)
Gentle introduction to multi-agent reinforcement learning
Recent studies show some impressive applications of reinforcement learning algorithms in sequential decision-making problems. In my talk, I will focus on problems that involve controlling a group of agents, i.e. multi-agent reinforcement learning. Though that domain shares clear similarities with th...
2022-01-27, godz. 12:15, meet.google.com/ooi-zxye-dxa
Jakub Świątkowski (Uniwerystet Warszawski)
Tutorial on deep learning generative models for speech synthesis
Speech synthesis has important applications in virtual assistants, voice interfaces, and accessibility. There has been rapid progress in the quality of speech synthesis systems in recent years thanks to deep learning generative models....
2021-12-16, godz. 12:15, meet.google.com/ooi-zxye-dxa
Jan Ludziejewski (Uniwerystet Warszawski)
The OpenAI Jukebox was a groundbreaking model in sound generation and is still considered to be the state-of-the-art in the music modeling task. It consists of two separate networks, Vector Quantization Variational Autoencoder, which strongly compresses the raw waveform into a series of discret...
2021-12-02, godz. 12:15, meet.google.com/ooi-zxye-dxa
Piotr Tempczyk (Uniwersytet Warszawski)
LIDL: Local Intrinsic Dimension estimation using approximate Likelihood
Understanding how neural networks work is one of the most important questions in machine learning research. Their performance is connected with the shape of the data manifold. The structure of this manifold can be explored with local intrinsic dimension (LID) estimat...
2021-11-18, godz. 12:15, meet.google.com/ooi-zxye-dxa
Michał Zając (Uniwersytet Jagielloński)
Continual World: Continual learning meets reinforcement learning
First, I'll introduce the setup of continual learning. I'll talk about how various methods mitigate catastrophic forgetting and improve forward transfer. I'll also show what are the trade-offs and requirements for continual learning methods. In the second part, I will introduce our be...
2021-11-04, godz. 12:15, meet.google.com/ooi-zxye-dxa
Konrad Czechowski (Uniwerystet Warszawski)
Subgoal Search For Complex Reasoning Tasks
I will present our publication accepted to NeurIPS 2021. We proposed a method that improves search guided by neural networks in combinatorially complex domains. Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievabl...
2021-10-21, godz. 12:15, online seminar: meet.google.com/ooi-zxye-dxa
Łukasz Kuciński (IM PAN)
We will talk about our recent compositionality paper accepted at NeurIPS 2021. Communication is compositional if complex signals can be represented as a combi-nation of simpler subparts. In this paper, we theoretically show that inductive biases on both the training framework and the data...
2021-06-17, godz. 12:15, google meet (meet.google.com/yew-oubf-ngi)
Sebastian Jaszczur
Sparsity in Efficient Transformers
Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study sparse variants for all layers in the Transformer and propos...
2021-05-06, godz. 12:15, meet.google.com/yew-oubf-ngi
Piotr Kozakowski
Q-Value Weighted Regression: Reinforcement Learning with Limited Data
Sample efficiency is a major challenge in the current Reinforcement Learning (RL) systems. Another is robustness - it is hard to find one RL algorithm that will perform well in a variety of settings. I am going to present QWR - a novel RL algorithm that performs on-par with Soft Actor Critic (...
