Abstract

Developing documentation guidelines and easy-to-use templates for datasets and models is a challenging task, especially given the variety of backgrounds, skills, and incentives of the people involved in the building of natural language processing (NLP) tools. Nevertheless, the adoption of standard documentation practices across the field of NLP promotes more accessible and detailed descriptions of NLP datasets and models, while supporting researchers and developers in reflecting on their work. To help with the standardization of documentation, we present two case studies of efforts that aim to develop reusable documentation templates -- the HuggingFace data card, a general purpose card for datasets in NLP, and the GEM benchmark data and model cards with a focus on natural language generation. We describe our process for developing these templates, including the identification of relevant stakeholder groups, the definition of a set of guiding principles, the use of existing templates as our foundation, and iterative revisions based on feedback.

Abstract

Around 40% of the world’s population is currently without access to the Internet. The digital divide is due to the high cost of provisioning these services and the low return on investment for network operators. We propose using 5G network slicing with multi-tenancy (also known as neutral host networks (NHN)) for macro-cells and small cells in rural areas to reduce the costs. This paper investigates the techno-economic feasibility of using rural 5G NHN to minimise the digital divide. A generic model is developed to analyse the techno-economic analysis of 5G NHN deployment around the world, with a special focus on rural areas where no MNO is interested in providing services. To understand the application, it is applied to the Indian scenario. First, a discussion on existing infrastructure, competition and statistics for Indian telecommunications is presented. Next, the technical requirements are analysed using the key performance indicators (KPI) required for the rural 5G NHN for the Indian scenario. The study also analyses the relationship between coverage, investment in the network, the number of subscribers, investment time, demand, the investment per user and sensitivity analysis to understand the feasibility of the proposed solution for Indian villages with different input conditions. Later, a case study is carried out based on the proposed approach, along with coverage modelling for a few Indian villages having different topologies. The results show that 5G NHN using network slicing can significantly reduce the total investment required for providing 5G services in rural areas. Furthermore, the study shows that rural 5G NHN is a

Abstract

Generative Adversarial Networks (GANs) are by far the most successful generative models. Learning the transformation which maps a low dimensional input noise to the data distribution forms the foundation for GANs. Despite their application in various domains, they are prone to certain challenges like mode collapse and unstable training. To overcome the challenges, researchers have proposed novel loss functions, architectures, and optimization methods. Unlike the previous approaches, we focus on the input noise and its role in the generation in our work here. We aim to quantitatively and qualitatively study the effect of the dimension of the input noise on the performance of GANs. For quantitative measures, typically Fréchet Inception Distance (FID) and Inception Score (IS) are used as performance measure on image data-sets. We compare the FID and IS values for DCGAN and WGAN-GP. We use three different image data-sets – each consisting of different levels of complexity. Our experiments show that the right dimension of input noise for optimal results depends on the data-set and architecture used. We also observe that the state of the art performance measures does not provide enough

Abstract

Datasets play an important role in driving innovation in algorithms and architectures for supervised deep learning tasks. Numerous datasets exist for images, language translation, etc. One of the interesting challenge problems for deep learning is to solve high school problems in mathematics and sciences. To this end, a comprehensive set of dataset containing hundreds of millions of samples, and the generation modules is required that can propel research for these problems. In this paper, a large set of datasets covering mathematics and science problems is proposed, and the dataset generation codes are proposed. Test results on the proposed datasets for character-to-character transformer architecture show promising results with test accuracy above 95%, however, for some datasets it shows test accuracy of below 30%

Abstract

Speech-to-Speech Machine Translation (SSMT) applications and services use a three-step process. Speech recognition is the first step to obtain transcriptions. This is followed by text-to-text language translation and, finally, synthesis into text-speech. As data availability and computing power improved, these individual steps evolved. However, despite significant progress, there is always the error of the first stage in terms of speech recognition, accent, etc. Having traversed the speech recognition stage, the error becomes more prevalent and decreases very often. This chapter presents a complete pipeline for transferring speaker intent in SSMT involving humans in the loop. Initially, the SSMT pipeline has been discussed and analyzed for broadcast speeches and talks on a few sessions of Mann Ki Baat, where the source language is in Hindi, and the target language is in English and Telugu. To perform this task, industry-grade APIs from Google, Microsoft, CDAC, and IITM has been used for benchmarking. Later challenges faced while building the pipeline are discussed, and potential solutions have been introduced. Later this chapter introduces a framework developed to

Abstract

The use of cell phones inside an aircraft is prohibited because cell phones pose a safety risk to aircraft systems and operations. Personal Electronic Device (PED) policies exist to avoid radio interference caused by the operation of cell phones in flight. The PED policies require passengers and crew members to stow away or use Airplane Mode when traveling by air. This paper focuses on studying the existing PED policies for the usage of cell phones inside an aircraft. We also study reports presenting technical data on why such a policy is required. We have also included individual experiences reported by passengers while travelling on how people react and behave when asked to turn on Airplane Mode or switch off their electronic devices. After establishing the problem, we discuss solutions that might switch off cell phones in flight or enable Airplane Mode automatically without any human intervention. We deliberate on three potential solutions (a) Mobile phone jammer, (b) Cellular Pico-cell onboard, (c) an Automatic Airplane Mode system. We propose creating an Automatic Airplane Mode System. We discuss various aspects of the proposed system, technical development choices and social features considerations. We discuss system development details and architecture along with the proposed uses of the system proposed. In the end, we conclude our work and list out some future scope activities.

Abstract

In this paper, we present a novel approach for domain adaptation in Neural Machine Translation which aims to improve the translation quality over a new domain. Adapting new domains is a highly challeng- ing task for Neural Machine Translation on limited data, it becomes even more diffi- cult for technical domains such as Chem- istry and Artificial Intelligence due to spe- cific terminology, etc. We propose Domain Specific Back Translation method which uses available monolingual data and gen- erates synthetic data in a different way. This approach uses Out Of Domain words. The approach is very generic and can be applied to any language pair for any do- main. We conduct our experiments on Chemistry and Artificial Intelligence do- mains for Hindi and Telugu in both direc- tions. It has been observed that the usage of synthetic data created by the proposed algorithm improves the BLEU scores sig- nificantly

Abstract

In recent times, quadrotors have become immensely applicable in scenarios such as relief operations, infrastructure maintenance, search-and-rescue missions etc. A key control design challenge arises in these applications when the quadrotor has to manoeuvre through constrained spaces such as narrow windows, pipelines in the presence of external disturbances and parametric uncertainties: such conditions necessitate the controller to guarantee predefined tracking accuracy so as to not violate the constraints and simultaneously tackle uncertainties. However, state-of-the-art controllers dealing with constrained system motion are not applicable either for an underactuated system like quadrotor or for an uncertain system dynamics. This work proposes a robust controller that enables the quadrotor to follow a trajectory with predefined tracking accuracy in constrained space as well as to tackle uncertainties stemming from imprecise system modelling and external disturbances. The closed-loop system stability is analysed via the Barrier Lyapunov approach and the effectiveness of the proposed controller is validated via simulation with state of the art.

Abstract

The ramp generator is a crucial circuit component in the design of switching power supply, analog to digital converters, CMOS image sensors, and many other essential circuits. Conventionally, the ramp generator has been implemented with a CMOS comparator that works on the hysteresis principle, which leads to an inherent systemic delay. This paper aims at improving the overall circuit speed by proposing the design of a ramp generator using CMOS proteretic comparator in 180nm TSMC process. It is established from the post-layout simulation that a speedup of 25% is achieved by replacing a hysteretic comparator with a proteretic comparator, and this is done with a trade-off in power consumption and circuit area.

Abstract

The question of how the human brain represents information, and if insights from this knowledge help us in formulating better deep learning algorithms, is still open. This paper attempts to address these questions by investigating the brain responses when participants viewed images of objects belonging to a variety of categories. We adopt the representational similarity analysis (RSA) framework wherein the brain responses are projected into a representational dissimilarity (RD) space so that responses from multiple subjects can be assessed on a common basis. We performed RSA of the brain responses of 15 participants on a set of 92 images (from the Algonauts challenge data set) Cichy et al. (The Algonauts project: a platform for communication between the sciences of biological and artificial intelligence 2019 [4]). The results reveal that human brain responses exhibit appropriate qualitative similarities observed in the image space. We then evaluated various deep networks such as VGGnet, AlexNet, and Inception in Siamese configuration with RD-loss function and identified hidden layers that had maximal similarity to human RD matrices (RDM). The best layers then were subjected to further analysis by looking at the image pairs corresponding to high and