Go to JKU Homepage
LIT Artificial Intelligence Lab
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

LIT AI Lab/ELLIS Unit Linz Seminar.

The LIT AI Lab kicks off the “LIT AI Lab/ ELLIS Unit Linz Seminar” in summer 2021, which shall bring together researchers and students interested in the field of Artificial Intelligence.

You can follow the talks online via zoom and/or in person (3G rules apply) as mentioned below.

Wednesday, 19 January 2022 at 01:00 pm
(Zoom Meeting - Link below)

Stefan Perko
Research Assistant (PhD student), Friedrich-Schiller-Universität Jena
joint work with Stefan Ankirchner

Approximating stochastic gradient descent with diffusions

Video of the Talk: https://youtu.be/Q9R6qm5iv1k, opens an external URL in a new window

 

To participate enter with the following Zoom-Link:

https://jku.zoom.us/j/91383246249?pwd=eVcydG1mT1FZazNqUUcxeFFqeEYrdz09, opens an external URL in a new window

Meeting-ID: 913 8324 6249
Passwort: 271828


Abstract
In machine learning and especially in deep learning there is one algorithm that, including many of its variations, is used almost universally for training large and non-linear models: stochastic gradient descent (SGD).
Applying a SGD method for minimizing an objective gives rise to a discrete-time process of estimated parameter values. While the mathematical description is fairly simple, the behavior of the algorithm generally is not. In order to better understand the dynamics of the estimated values it is reasonable to approximate the discrete-time process with the solution of a differential equation. The resulting gradient flow equation describes the mean evolution of the SGD process very well. However, it does not account for the noise inherent in the SGD method.
For example it does not see the difference between different mini-batch sizes or between having an infinite list of fresh data versus a finite sample of data. To rectify this issue one can introduce a noise term to the gradient flow equation, turning it into a so called stochastic differential equation. A solution to the resulting equation is called a diffusion approximation to SGD.

In this talk we describe how to explicitly calculate and compare the errors of gradient flow and the so called first-order diffusion approximation. Further, we show that one can find an even better, second-order diffusion approximation. Finally, some applications of diffusion approximations are explored.

Wednesday, 1 September 2021 at 10am
Room S3 055 or via Zoom (link further below)

Thomas Koller
Hochschule Luzern Informatik

Challenging Human Supremacy: Evaluating Monte Carlo Tree Search and Deep Learning for the Trick Taking Card Game Jass

Abstract: Despite the recent successful application of Artificial Intelligence (AI) to games, the performance of cooperative agents in imperfect information games is still far from surpassing humans. Cooperating with teammates whose play-styles are not previously known poses additional challenges to current state-of-the-art algorithms. In the Swiss card game Jass, coordination within the two opposing teams is crucial for winning. Since verbal communication is forbidden, the only way to transmit information within the team is through a player’s play-style. This makes the game a particularly suitable candidate subject to continue the research on AI in cooperation games with hidden information. In this work, we analyse the effectiveness and shortcomings of several state-of-the-art algorithms (Monte Carlo Tree Search (MCTS) variants and Deep Neural Networks (DNNs)) at playing the Jass game.

 

Zoom link: https://jku.zoom.us/j/98246734423?pwd=QXJ4ekJBUkNHb3M0bXFKVEVuQ1h1dz09 , opens an external URL in a new window

Thursday, 19 August 2021 at 2:30pm
Zoom (link below)

Alexander Kolesnikov
Google Switzerland

New Vision Architectures Beyond CNNs

Abstract: Convolutional Neural Networks (CNNs) have been solely dominating the field of computer vision for nearly a decade. In this talk I will present two recent papers that propose new and highly competitive architecture classes for computer vision. In the first part I will present the Vision Transformer model (ViT), which is almost identical to the standard transformer model used in natural language processing, but happens to work surprisingly well for vision applications. In the second part of the talk, I will present the MLP-mixer model: an all-MLP architecture for vision. It can be seen as a simplified ViT model without the self-attention layer. Nevertheless, it also demonstrates strong results across a wide range of vision applications.

 

Zoom link: https://jku.zoom.us/j/98246734423?pwd=QXJ4ekJBUkNHb3M0bXFKVEVuQ1h1dz09, opens an external URL in a new window (Meeting-ID: 982 4673 4423, Passwort: 550113)

Wednesday, 11 August 2021 at 10am
Lecture hall 19 or via Zoom (link further below)

Richard Küng
Institute for Integrated Circuits, Johannes Kepler University Linz

Provably efficient machine learning for quantum physics

Abstract: Classical machine learning (ML) provides a potentially powerful approach to solving challenging problems in quantum physics and chemistry. However, the advantages of ML over more traditional methods have not been firmly established. We prove that classical ML algorithms can efficiently predict ground state properties of a physical system, after learning from data obtained by measuring related systems. We also prove that classical ML algorithms can efficiently classify a wide range of quantum phases of matter. Our arguments are based on the concept of a classical shadow, a succinct classical description of a quantum state that can be constructed in feasible quantum experiments and be used to predict many properties of the state.
 
This is joint work with Robert Huang (Caltech), Giacomo Torlai (AWS), Victor Albert (University of Maryland) and John Preskill (Caltech+AWS).

 

Zoom link: https://jku.zoom.us/j/98246734423?pwd=QXJ4ekJBUkNHb3M0bXFKVEVuQ1h1dz09, opens an external URL in a new window (Meeting-ID: 982 4673 4423, Passwort: 550113)