Advancing the state of the art

Generative Adversarial Networks are plagued by training instability, despite considerable research effort. Progress has been made on this topic, but many of the proposed interventions are complicated, computationally expensive, or both. In this work, we propose a simple and effective training stabilizer based on the notion of Consistency Regularization - a popular technique in the Semi-...

Despite the widespread adoption of Transformer models for NLP tasks, the expressive power of these models is not well-understood. In this paper, we establish that Transformer models are universal approximators of continuous permutation equivariant sequence-to-sequence functions with compact support, which is quite surprising given the amount of shared parameters in these models. Furthermore,...

Voice assistants have been successfully adopted for simple, routine tasks, such as asking for the weather or setting an alarm. However, as people get more familiar with voice assistants, they may increase their expectations for more complex tasks, such as exploratory search — e.g., “What should I do when I visit Paris with kids? Oh, and ideally not too expensive.” Compared to simple search...

Light fields capture both the spatial and angular rays, thus enabling free-viewpoint rendering and custom selection of the focal plane. Scientists can interactively explore pre-recorded microscopic light fields of organs, microbes, and neurons using virtual reality headsets. However, rendering high-resolution light fields at interactive frame rates requires a very high rate of texture sampling,...

The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision. In this paper, we summarize the results of (Locatello et al. 2019b) and focus on their implications for practitioners. We discuss the theoretical result showing that the unsupervised learning of disentangled...

Machine Learning (ML) research has primarily focused on improving the accuracy and efficiency of the training algorithms while paying much less attention to the equally important problem of understanding the data and monitoring the quality of the data fed to ML. Irrespective of the ML algorithms used, data errors can adversely affect the quality of the generated model. This indicates that we...

The future of work is speculated to undergo profound change with increased automation. Predictable jobs are projected to face high susceptibility to technological developments. Many economies in Global South are built around outsourcing and manual labour, facing a risk of job insecurity. In this paper, we examine the perceptions and practices around automated futures of work among a population...

Background: Automated machine-learning systems are able to de-identify electronic medical records, including free-text clinical notes. Use of such systems would greatly boost the amount of data available to researchers, yet their deployment has been limited due to uncertainty about their performance when applied to new datasets. Objective: We present practical options for clinical note de-...