Search

The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has significantly lowered the computational overhead for conducting scientific research in neural architecture search (NAS). Although they have been widely adopted and used to tune real-world NAS algorithms, these benchmarks are limited to small search spaces and focus solely on image classification. Recently, several new NAS benchmarks have been introduced that cover significantly larger search spaces over a wide range of tasks, including object detection, speech recognition, and natural language processing. However, substantial differences among these NAS benchmarks have so far prevented their widespread adoption, limiting researchers to using just a few benchmarks. In this work, we present an in-depth analysis of popular NAS algorithms and performance prediction methods across 25 different combinations of search spaces and datasets, finding that many conclusions drawn from a few NAS benchmarks do not generalize to other benchmarks. To help remedy this problem, we introduce NAS-Bench-Suite, a comprehensive and extensible collection of NAS benchmarks, accessible through a unified interface, created with the aim to facilitate reproducible, generalizable, and rapid NAS research. Our code is available at https://github.com/automl/naslib., Comment: ICLR 2022

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously problematic, since they require weight sharing - something real neurons simply cannot do. Consequently, while neurons in the brain can be locally connected (one of the features of convolutional networks), they cannot be convolutional. Locally connected but non-convolutional networks, however, significantly underperform convolutional ones. This is troublesome for studies that use convolutional networks to explain activity in the visual system. Here we study plausible alternatives to weight sharing that aim at the same regularization principle, which is to make each neuron within a pool react similarly to identical inputs. The most natural way to do that is by showing the network multiple translations of the same image, akin to saccades in animal vision. However, this approach requires many translations, and doesn't remove the performance gap. We propose instead to add lateral connectivity to a locally connected network, and allow learning via Hebbian plasticity. This requires the network to pause occasionally for a sleep-like phase of "weight sharing". This method enables locally connected networks to achieve nearly convolutional performance on ImageNet and improves their fit to the ventral stream data, thus supporting convolutional networks as a model of the visual stream.

In recent years, deep learning-based automated personality trait detection has received a lot of attention, especially now, due to the massive digital footprints of an individual. Moreover, many researchers have demonstrated that there is a strong link between personality traits and emotions. In this paper, we build on the known correlation between personality traits and emotional behaviors, and propose a novel multitask learning framework, SoGMTL that simultaneously predicts both of them. We also empirically evaluate and discuss different information-sharing mechanisms between the two tasks. To ensure the high quality of the learning process, we adopt a MAML-like framework for model optimization. Our more computationally efficient CNN-based multitask model achieves the state-of-the-art performance across multiple famous personality and emotion datasets, even outperforming Language Model based models.

A unique identification for citizens can lead to effective governance to manage and provide citizen-centric services. While ensuring this service, privacy of the citizens needs to be preserved. Aadhaar, the identification system by UIDAI has faced some critics regarding its privacy preserving feature. This paper discusses those concerns in Aadhaar system and proposed a new model for the Aadhaar system. The proposed solution is aimed to address the issue of collusion of third party service providers and profiling of Aadhaar users. The proposed solution uses a distributed model capturing the Aadhaar system, in which data of users is decentralized and stored in zonal office's databases as well as the CIDR. The proposed solution provides the functioning of the authentication process of the Aadhaar system more effective, as it reduces the number of requests being handled directly by the CIDR and also tackles the concern of correlation of data., Comment: 8 pages, 2 figures

Recently, the automatic prediction of personality traits has received increasing attention and has emerged as a hot topic within the field of affective computing. In this work, we present a novel deep learning-based approach for automated personality detection from text. We leverage state of the art advances in natural language understanding, namely the BERT language model to extract contextualized word embeddings from textual data for automated author personality detection. Our primary goal is to develop a computationally efficient, high-performance personality prediction model which can be easily used by a large number of people without access to huge computation resources. Our extensive experiments with this ideology in mind, led us to develop a novel model which feeds contextualized embeddings along with psycholinguistic features toa Bagged-SVM classifier for personality trait prediction. Our model outperforms the previous state of the art by 1.04% and, at the same time is significantly more computationally efficient to train. We report our results on the famous gold standard Essays dataset for personality detection.

Recently, the automatic prediction of personality traits has received a lot of attention. Specifically, personality trait prediction from multimodal data has emerged as a hot topic within the field of affective computing. In this paper, we review significant machine learning models which have been employed for personality detection, with an emphasis on deep learning-based methods. This review paper provides an overview of the most popular approaches to automated personality detection, various computational datasets, its industrial applications, and state-of-the-art machine learning models for personality detection with specific focus on multimodal approaches. Personality detection is a very broad and diverse topic: this survey only focuses on computational approaches and leaves out psychological studies on personality detection.

We investigate the electronic properties of ballistic planar Josephson junctions with multiple superconducting terminals. Our devices consist of monolayer graphene encapsulated in boron nitride with molybdenum-rhenium contacts. Resistance measurements yield multiple resonant features, which are attributed to supercurrent flow among adjacent and non-adjacent Josephson junctions. In particular, we find that superconducting and dissipative currents coexist within the same region of graphene. We show that the presence of dissipative currents primarily results in electron heating and estimate the associated temperature rise. We find that the electrons in encapsulated graphene are efficiently cooled through the electron-phonon coupling., Comment: 3 Figures, 6 pages

Coupling superconductors to quantum Hall edge states is the subject of intense investigation as part of the ongoing search for non-abelian excitations. Our group has previously observed supercurrents of hundreds of picoamperes in graphene Josephson junctions in the quantum Hall regime. One of the explanations of this phenomenon involves the coupling of an electron edge state on one side of the junction to a hole edge state on the opposite side. In our previous samples, these states are separated by several microns. Here, a narrow trench perpendicular to the contacts creates counterpropagating quantum Hall edge channels tens of nanometres from each other. Transport measurements demonstrate a change in the low-field Fraunhofer interference pattern for trench devices and show a supercurrent in both trench and reference junctions in the quantum Hall regime. The trench junctions show no enhancement of quantum Hall supercurrent and an unexpected supercurrent periodicity with applied field, suggesting the need for further optimization of device parameters., Comment: 9 pages, 5 figures

In this study, we examine multiple encapsulated graphene Josephson junctions to determine which mechanisms may be responsible for the supercurrent observed in the quantum Hall (QH) regime. Rectangular junctions with various widths and lengths were studied to identify which parameters affect the occurrence of QH supercurrent. We also studied additional samples where the graphene region is extended beyond the contacts on one side, making that edge of the mesa significantly longer than the opposite edge. This is done in order to distinguish two potential mechanisms: a) supercurrents independently flowing along both non-contacted edges of graphene mesa, and b) opposite sides of the mesa being coupled by hybrid electron-hole modes flowing along the superconductor/graphene boundary. The supercurrent appears suppressed in extended junctions, suggesting the latter mechanism.