In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ from domai...
Correlations between psychological and physiological phenomena form the basis for different medical and scientific disciplines, but the nature of this relation has not yet been fully understood. One conceptual option is to understand the mental as...
Throaway for reasons. I just want to share my experience and my current vulnerabilities. I have been married for 2 years and I have a baby daughter right now. These past few days I'm in touch with a...
In recent years, self-supervised learning has emerged as a powerful tool to harness abundant unlabelled data for representation learning and has been broadly adopted in diverse areas. However, when applied to molecular representation learning (MRL),...
The emergence of generative AI chatbots such as ChatGPT has prompted growing public and academic interest in their role as informal mental health support tools. While early rule-based systems have been around for several years, large language models...
Surface modification of different materials exposed to an environment typical for hot cathode ionisation vacuum gauges was investigated. Such environment has been generated in a specially designed setup which simulates conditions in a Bayard-Alpert i...
In this paper, AzarNet, a deep neural network (DNN), is proposed to recognizing seven different Dastgahs of Iranian classical music in Maryam Iranian classical music (MICM) dataset. Over the last years, there has been remarkable interest in employing...
In this paper, we study the multi-armed bandit problem in the batched setting where the employed policy must split data into a small number of batches. While the minimax regret for the two-armed stochastic bandits has been completely characterized in...
Topic modelling has been a successful technique for text analysis for almost twenty years. When topic modelling met deep neural networks, there emerged a new and increasingly popular research area, neural topic models, with over a hundred models deve...
I've been in the "back room HR discussions" about which employees should vs. should not get promoted. I've seen what really gets the attention of senior leaders and what doesn't, etc. I see my friend...
Although many models have been proposed, the physical mechanisms responsible for the formation of low-mass brown dwarfs are poorly understood. The multiplicity properties and minimum mass of the brown-dwarf mass function provide critical empirical di...
Several techniques have been proposed to detect vulnerable Spectre gadgets in widely deployed commercial software. Unfortunately, detection techniques proposed so far rely on hand-written rules which fall short in covering subtle variations of known...
President Donald Trump’s decision to topple the Iranian regime is threatening to torch an oil market his administration has been at pains to keep cool since he returned to office.
>Nvidia CEO Jensen Huang told employees this week that the company has been pushed into a no-win situation by mounting fears of an AI bubble, even as it continues to post blockbuster results, accor...
Online data scraping has taken on new dimensions in recent years, as traditional scrapers have been joined by new AI-specific bots. To counteract unwanted scraping, many sites use tools like the Robots Exclusion Protocol (REP), which places a robots$...
Iridates have attracted much interest in the last decade for their novel magnetism emerging in the limit of strong spin-orbit coupling and possible unconventional superconductivity. A standard for growing iridate single crystals has been the flux met...
Notions of Darwinian selection have been implicit in economic theory for at least sixty years. Richard Nelson and Sidney Winter have argued that while evolutionary thinking was prevalent in prewar economics, the postwar Neoclassical school became a...
The sharpness-aware minimization (SAM) algorithm and its variants, including gap guided SAM (GSAM), have been successful at improving the generalization capability of deep neural network models by finding flat local minima of the empirical loss in tr...
Steering is a manifestation of quantum correlations that embodies the Einstein-Podolsky-Rosen (EPR) paradox. While there have been recent attempts to quantify steering, continuous variable systems remained elusive. We introduce a steering measure for...
The electronic structure of Me[N(CN)$_2$]$_2$ (Me=Mn, Fe, Co, Ni, Cu) molecular magnets has been investigated using x-ray emission spectroscopy (XES) and x-ray photoelectron spectroscopy (XPS) as well as theoretical density-functional-based methods...