Leon Sixt

Machine Learning PhD Student | Interpretability | FU Berlin | him/he

[YoussefNader @Youssef_M_Nader]

I am about to miss the celebration for winning the Vesuvius Grandprize! This is the second time I am missing a Prize Ceremony for winning a Vesuvius Challenge in the USA and I started the visa application process as so as the prize was announced. This is incredibly frustrating and depressing, is there a way to expedite the process? The Ceremony is on March 16th. @usconsfrankfurt @usbotschaft @USAmbGermany I understand that you receive an overwhelming volume of applications and requests, but is there anything that could be done?

[Leon Sixt @LeonSixt]

Finally, the best part of my PhD was to collaborate with many amazing people:
@tlandgraf, @Youssef_M_Nader, @martnsch, @oanaucs, @GranzMaximilian, @karlschulz_ and also during my internship at Google with @_beenkim and @martin_maas.

[Leon Sixt @LeonSixt]

In a follow up work https://t.co/5AKIaPHLmO, we found out that the positive matrices were to blame and that also other methods suffer from similar limitations. We recently updated the paper to fix a minor mistake in the proof and now also include a proof on the convergence speed.

[Leon Sixt @LeonSixt]

- my impression is that XAI methods are in general too unreliable to be actually useful,
- I would bet that the alignment of AI systems will be resolved without using XAI method

[Leon Sixt @LeonSixt]

In the IBA paper, we also made another observation: the LRP's z+ rule fails the weight-randomization sanity check. Why does one of the most cited attribution methods return the same result even after the weights are partially randomized?

[Leon Sixt @LeonSixt]

We presented IBA as a method to explain classifiers. We were quite impressed to see how well the Information Bottleneck Attribution did in several empirical proxy tasks and received an ICLR Oral presentation for it: https://t.co/dPWRt8eYUf

[Leon Sixt @LeonSixt]

I am very happy to celebrate my PhD defense. I want to take this opportunity to share my unique path through my PhD and share a small conclusion.

[Leon Sixt @LeonSixt]

When starting my PhD, my original plan was to improve unsupervised learning using explainability methods. Our first paper with @karlschulz_ was supposed to be a step towards this direction, identifying the most relevant parts in an image using information theoretic principles.

[Leon Sixt @LeonSixt]

Before starting my PhD, I already had my first academic success during my bachelors: https://t.co/EVxalgkJKg Probably our paper was the first to apply GANs to a real-world problem, in this case the identification of honey bees.

[YoussefNader @Youssef_M_Nader]

It has been absolutely phenomenal working on the Vesuvius Challenge. The vision from @natfriedman and the foundation layed down by Prof. Seales and his team, make me every bit grateful to have the opportunity to score this touchdown!

[Leon Sixt @LeonSixt]

Excited to see Jakob and Thore launch @PheironInc! Having had the pleasure of working with them, I highly recommend joining their team. If you're a ML Engineer, check out their latest job openings: https://t.co/KMOaPQeUsj #MachineLearning #CareerOpportunities #MachineLearning

[Jakob Steinfeldt, MD @SteinfeldtJakob]

Over the past few months, @gogothorr and I have been heads down building @PheironInc . Our platform extracts disease markers from biomedical data to aim right: identifying the right targets for diseases and the right populations for clinical trials.

This is personal to us:

[Manuel @xmxanuel]

Asking GPT-4 to think step-by-step and to reason about input validation and require statements can find the bug.😽
https://t.co/mmbrlZppIf

[Explainable Machine Learning @ExplainableML]

Our workshop continues with two very interesting spotlights 🔍 - on the gap between explanations and the explained model by @LeonSixt, and the use of Explainable AI for Scalable and Trustworthy AI by @coallaoh!