(The talk will be given in English)

Speaker:     Dr. Assaf Shocher

                              NVIDIA

Monday, December 23^rd, 2024

12:00 - 13:00

Making Neural Networks Linear Again: Projection and Beyond

Abstract

Every day, somewhere, a researcher mutters, “If only neural networks were linear, this problem would be solved”. Linear operations offer powerful tools: projection onto subspaces, eigen decomposition, and more. This talk explores their equivalents in the non-linear world of neural networks, with a special focus on projection, generalized by idempotent operators- operators that satisfy f(f(x)) = f(x).

Idempotent Generative Network (IGN) is a generative model that is trained by enforcing two main objectives: (1) target distribution data map to themselves f(x) = x, defining the target manifold, and (2) latents project onto this manifold via the idempotence condition f(f(z)) = f(z). IGN generates data in a single step, but can iteratively refine, and projects corrupted data back onto the distribution.

This projection ability gives rise to Idempotent Test-Time Training (IT³), a method to adapt models at test time using only current out-of-distribution (OOD) input. During training, the model f receives an input x along with either the ground truth label y or a neutral "don't know" signal ∅. At test-time, given corrupted/OOD input x, a brief training session minimizes ||f(x, f(x, ∅)) - f(x, ∅)||, making f(x,⋅) idempotent. IT³ works across architectures and tasks, demonstrated for MLPs, CNNs, and GNNs on corrupted images, tabular data, OOD facial age prediction, and aerodynamic predictions.

Finally, I'll ask: "Who says neural networks are non-linear?" They're only non-linear with respect to the standard vector spaces! In an ongoing work, we construct vector spaces X, Y with their own addition, negation, and scalar multiplication, where f: X → Y becomes truly linear. This enables novel applications including spectral decomposition, zero-shot solutions to non-linear inverse problems via Pseudo-Inverse, and architecture-enforced idempotence.

Short Bio

I am a postdoctoral researcher at NVIDIA. Prior to that I was a postdoctoral fellow at UC Berkeley, working with Alyosha Efros, and a visiting researcher at Google. I received my PhD from the Weizmann Institute of Science, where I was advised by Michal Irani. I have bachelor's degrees in Physics and EE from Ben-Gurion University. My prizes and honors include the Rothschild postdoctoral fellowship, the Fulbright postdoctoral fellowship, John F. Kennedy award for outstanding Ph.D. at the Weizmann Institute, and the Blavatnik award for CS Ph.D. graduates.

השתתפות בסמינר תיתן קרדיט שמיעה = עפ"י רישום שם מלא + מספר ת.ז. בטופס הנוכחות שיועבר באולם במהלך הסמינר

:Abstract

Histology and Cytology play a critical role in biomedical research by enabling the detection and analysis of tissue and cell- Morphology, abnormalities, protein and RNA expression and treatments effects. Over the past decade, significant advancements have transformed this field, including the development of synthetic biomarkers and new methods that enable the use of multiple fluorescence-labeled antibodies and RNA probes on single sample section. Additionally, innovations in confocal microscopy and high-resolution slides scanning microscopes have greatly improved imaging capabilities. The emergence of Machine learning based Quantitative Image Analysis- that enables precise analysis of histology and cytology large datasets (i.e. cell populations, distances between cell populations, expression level in each cell population), patterns recognition (i.e. blood vessels populations detection and analysis, neuronal and collagen fibers parameters analysis etc.).
Together- these advancements in Histology and cytology, microscopy and image analysis- enable researchers to extract high quantity of data from each sample section, enabling accurate quantitative evaluation of basic research data and treatments effects.
In this seminar, I will present the main Histology, Cytology and Machine learning based Quantitative Image Analysis (HCA) methodologies and innovations in relevant research fields, providing examples in different cells, tissues and animal models. This will equip researchers with a better understanding of .how to apply these cutting-edge HCA techniques to their own .studies 

  -סמינר זה יחשב כסמינר שמיעה לתלמידי תואר שני ושלישי-  This Seminar Is Considered A Hearing Seminar For Msc/Phd Students