Gal Katzhendler

I research Machine Learning at the Hebrew University, as part of Prof. Amit Daniely’s lab.

My research is focused around Machine Learning Theory and (attempting at) creating mathematical foundations for Deep Learning. I’m also interested in Complex Systems, Kolmogorov Complexity, Audio Digital Signal Processing, Topological Data Analysis, and making things differentiable.

Feel free to contact me via email to discuss or collaborate on any of my interests.

news

Feb 22, 2022	I’ve started my PhD studies under the supervision of Prof. Amit Daniely.

selected publications

Potential upside of high initial visual acuity?

Daphna Weinshall Gal Katzhendler

Proceedings of the National Academy of Sciences 2019

Abs PDF

Vogelsang et al. (1) argue that high initial visual acuity in children, who underwent late treatment of congenital blindness, may be responsible for subsequent impairments in configural face analysis. This hypothesis offers an exciting alternative to the standard explanation of a critical period for the ensuing impairment, which could have dramatic implications on the follow-up treatment of such children. However, close inspection of the supporting computational argument provided in ref. 1 casts doubt on this conclusion. After broadening the analysis, we conclude that the computational study in ref. 1 cannot be used as evidence that initial exposure to low-resolution images is necessarily beneficial. We were also unable to confirm another proposed implication, that initial presentation of low-resolution images can improve the generalization performance of artificial neural networks in general, by promoting the development of larger receptive fields (2).
Approximate Description Length, Covering Numbers, and VC Dimension

Gal Katzhendler Amit Daniely

2022

Abs arXiv PDF

Recently, Daniely and Granot introduced a new notion of complexity called Approximate Description Length (ADL). They used it to derive novel generalization bounds for neural networks, that despite substantial work, were out of reach for more classical techniques such as discretization, Covering Numbers and Rademacher Complexity. In this paper we explore how ADL relates to classical notions of function complexity such as Covering Numbers and VC Dimension. We find that for functions whose range is the reals, ADL is essentially equivalent to these classical complexity measures. However, this equivalence breaks for functions with high dimensional range.