Integreat has been selected as one of 10 finalists at Google.org’s impact challenge in the category “lighthouse projects”! This secures 250,000€ of funding that we will use to expand on the job market capabilities.
Summer Internship work is out in ICLR! Automatic architecture search finds non-intuitive (at least to me) architecture including sine curves and division.
I’m really glad to have worked with a fantastic team at Salesforce Research, most closely with Stephen Merity and Richard Socher.
Paper + Reviews: https://openreview.net/forum?id=SkOb1Fl0Z
It’s done! I finished my Master’s Thesis which focused on the idea and implementation of recurrent neural networks in computer vision, inspired by findings in neuroscience. The two main applications of this technique shown here are the recognition of partially occluded objects and the integration of context cues.
There is a new project we are beginning to look into which analyzes today’s neural networks in terms of stability and plasticity.
More explicitly, we evaluate how well these networks can cope with changes to their weights and how well they can adapt to new information. Some preliminary results suggest that if weights in lower layers are perturbed, this has a more severe effect on performance than if higher layers are perturbed. This has a nice correlation to neuroscience where it is assumed that our hierarchically lower cortical layers in the visual cortex remain rather fixed over the years.
Update: we just uploaded a version to arXiv (https://arxiv.org/abs/1703.08245) which is currently under review at ICML.
Just presented our work on Recurrent Computations for Pattern Completion at the NIPS 2016 Brains & Bits Workshop!
It was an awesome conference, lots of new work and amazing individuals.
Here’s a really short summary, but I highly recommend going through the papers and talks:
- unsupervised learning and GANs are hot
- learning to learn is becoming hot
- new threshold for deep: 1202 layers
After some requests, I have uploaded my (really short) analysis of Google’s TensorFlow to arXiv: https://arxiv.org/abs/1611.08903.
It is really just a small seminar paper, the main finding is that while using any Machine Learning framework is generally a good idea, TensorFlow has a really good chance of sticking around due to its already widespread usage within Google and research coupled with a growing community.
My research focuses on a computational understanding of the neural mechanisms underlying natural intelligence in vision and language. To achieve this goal, I bridge Deep Learning, Neuroscience, and Cognitive Science, building artificial neural network models that match the brain’s neural representations in their internal processing and are aligned to human behavior in their outputs.
I completed my PhD at the MIT Brain and Cognitive Sciences department with Jim DiCarlo, following Bachelor’s and Master’s degrees in computer science at TUM, LMU, and UNA. Previous work includes research in human-like vision at Harvard, natural language processing + reinforcement learning at Salesforce, as well as several other projects in industry and two startups. My work has been recognized in the news at Science magazine, MIT News, and Scientific American.
I am currently a tenure-track assistant professor at EPFL at the Neuro-X institute, with appointments at the School of Life Sciences, and the School of Computer and Communication Sciences.
We just won the Integration Prize of the Government of Swabia with Integreat!
Although it’s been a while, I thought I’d upload my Bachelor’s Thesis for others to read: Scalable Database Concurrency Control using Transactional Memory.pdf.
The work consists of two parts:
Part 1 analyzes the constraints of Hardware Transactional Memory (HTM) and identifies data structures that profit most of this technique.
Part 2 attempts different implementations of HTM in MySQL’s InnoDB storage component and evaluates the results.