Seminar | TransferLab — appliedAI Institute

Seminar

The TransferLab Seminar is a platform where researchers and engineers share and discuss recent advances in AI/ML, striking a balance between accessibility and mathematical depth.

We organize comprehensive talks on ML, RL, DL and statistics, emphasizing both theoretical understanding and practical implementation. These range from introductory overviews to recent developments - and are open to all interested individuals!

Each talk, lasting about 45min followed by around 15min discussion, focuses on a specific topic related to our ongoing series topics. To stay informed, follow the appliedAI Institute on LinkedIn. If you’re interested in presenting your work, contact us. Recordings of past seminars are available on YouTube.

Upcoming Talks

Nothing here yet!

Previous Talks

The Levenshtein Transformer - Kristian Klemon

Mar 12, 2020

Although just released in 2017, the Transformer architecture (Vaswani et al.) has widely become the de facto standard approach for sequence-to-sequence problems like translation or abstractive text summarization. Despite the great success, the relatively slow inference process as well the general lack of flexibility due to the autoregressive nature of the generation process can quickly become a problem.

Generative Models

Kristian Klemon

Value based engineering: Method and application - Till Klein

Feb 27, 2020

There is much talk about AI and Ethics, but only few methods exist for applying ethical principles in practise, leading to a shortage of empirical examples. Based on a new standard by IEEE, the P7000 for addressing “ethical concerns during system design”, we analyse an AI use case that aims to find and nurture untapped talent in Africa, which, as such, comes with several ethical challenges from the outset.

The Information Bottleneck in RL - Robert Müller (appliedAI Institute)

Feb 20, 2020

State representations hold the promise of simplifying control, allowing a reinforcement learning (RL) agent to solve a task more quickly, and to generalize better to new tasks. While this representation can be learned in a multi-task setting, doing so requires manually constructing a suitable task distribution, an onerous requirement. Instead, we propose to learn a representation that encodes as few bits of the input as possible, subject to the constraint that the agent is still able to solve this task.

Fair ML in Budget-Constrained Decision Making - Patrick Tu

Feb 13, 2020

Fairness in Machine Learning. Motivation, background and research question. [Bak19F] Presented at KDD 2019 Explainable AI (XAI) for Accountability, Fairness, and Transparency Workshop. [Bak19D]. Presented at NeurIPS 2019 Human-Centric Machine Learning Workshop.

Markov Logic Networks: Construction, Learning and Inference - Michael Panchenko (appliedAI Initiative)

Feb 10, 2020

Markov logic networks provide a simple way for combining two seemingly rather different descriptions of data - first order logic and probability. While logical systems are a compact way to represent knowledge, they are too rigid for many real world applications. When trying to describe a dataset through logical relations between different features, a single data point violating them is enough to render the description incorrect.

Michael Panchenko

Conditional Random Fields with an application to Information Extraction - Faried Abu Zaid (appliedAI Institute)

Jan 29, 2020

In this week’s presentation we welcome a new colleague, Faried Abu Zaid, who will discuss Conditional Random Fields (CRFs), a kind of probabilistic graphical model (PGM) that is particularly well suited for classification tasks. He will give a short introduction to the field of PGMs with a special emphasis on CRFs.

Faried Abu Zaid

1 ...

11

... 18

Our Block Seminars

Methods and issues in Explainable AI

This seminar series explores the landscape of Explainable Artificial Intelligence (XAI) beyond the content in our training on XAI, and through a comprehensive selection of papers in the field. By the end of this series, participants will …

May 17, 2023

Uncertainty quantification for neural networks

In this seminar series, we review seminal and recent papers on uncertainty quantification that didn’t make it into our training on Bayesian ML.

Oct 22, 2022