RESEARCH

In this project we examine if and how echolocating bats can navigate over kilometers using only acoustic echoes. To study this, we generated a huge database of simulated echoes based on actual 3D maps of northern Israel, at a scale of dozens of kilometers.

This echoic information was examined, revealing the unique characteristics of different landscapes, that is - the statistics of the echo provide vast information about the landscape (e.g., whether it is a field, orchard, or lake and also sufficient information about unique landmarks that should allow echo-based navigation.

In the next part, we will construct a Navigation Neural-Network model that allows large-scale acoustic mapping. First, we used an Auto-Encoder network to represent the echoes in a low-dimensional space.

Next, we used Transformer LLMs to train a navigator that learns to navigate based on acoustic information. This network will rely on the previous ones in order to steer the agent’s navigation towards familiar locations. The network has already shown promising results. 

Remnants of more than 900 distinct literary works, known as the Dead Sea Scrolls, were discovered in Qumran. While these texts were undoubtedly written before 70 CE, the exact composition dates of each scroll and their literary connections are subjects of ongoing debate among scholars.

This project employs computational linguistic tools to address this issue. By utilizing machine learning models and algorithms, we compare the language of the DSS to Biblical Hebrew and Mishnaic Hebrew, aiming to uncover linguistic affinities between the scrolls and these corpora. This allows us to determine which texts retain more features of ancient Hebrew and which exhibit more innovative characteristics, potentially leading to a relative dating of the scrolls.

Coral reefs are deteriorating at an alarming rate worldwide. However, we lack cost-efficient high-resolution tools to monitor reef health.

Contrary to the prevailing view of the ocean as the realm of silence, it is increasingly recognized that sound in the ocean is both prevalent and diverse.

We aim to use the characteristics of ambient noise recordings to offer a near real-time tool for monitoring coral reef health at high spatial resolutions.

AI is revolutionizing all aspects of life. In our research, we leverage recent advances in AI to study evolution. Specifically, we have developed novel AI algorithms to reconstruct phylogenetic trees, which help us understand the relationships between species and how the diversity of life on Earth has evolved from ancestral species.

Reconstructing these trees is a well-known and challenging computational task. However, with the massive increase in data size, this task is becoming even more complex. Our AI-based algorithms aim to provide more accurate phylogenetic trees and make it feasible to analyze very large datasets, which are expected to become increasingly common in the coming decade.