Abstract

We embark on a hitherto unreported problem of an autonomous robot (self-driving car) navigating in dynamic scenes in a manner that reduces its localization error and eventual cumulative drift or Absolute Trajectory Error, which is pronounced in such dynamic scenes. With the hugely popular Velodyne-16 3D LIDAR as the main sensing modality, and the accurate LIDAR-based Localization and Mapping algorithm, LOAM, as the state estimation framework, we show that in the absence of a navigation policy, drift rapidly accumulates in the presence of moving objects. To overcome this, we learn actions that lead to drift-minimized navigation through a suitable set of reward and penalty functions. We use Proximal Policy Optimization, a class of Deep Reinforcement Learning methods, to learn the actions that result in drift-minimized trajectories. We show by extensive comparisons on a variety of synthetic, yet photo-realistic scenes made available through the CARLA Simulator the superior performance of the proposed framework vis-a-vis methods that do not adopt such policies.

Abstract

In addition to the three long-standing anomalies seen in the muon g − 2, RK(∗), and RD(∗) observables by various independent experiments, the CDF collaboration has found another significant one in the W boson mass. These anomalies might be intertwined at a fundamental level and have a single new physics explanation. In this paper, we investigate the possibility of whether these anomalies can be explained in a model of a weak-singlet S1 and a weak-triplet S3 scalar leptoquarks. We find that with an appropriate flavour ansatz and mass mixing between the S1 and S3 leptoquarks through a Higgs portal, the model can explain the four anomalies simultaneously while being consistent with potential spoilsport observables like R νν K(∗) .

Abstract

The U(1) extensions of the Standard Model contain a heavy neutral gauge boson Z 0 . If leptophobic, the boson can evade the stringent bounds from the dilepton resonance searches. In these extensions, righthanded neutrinos NR are also well-motivated by the gauge-anomaly cancellation and light-neutrino mass generation via seesaw mechanisms. The coexistence of a leptophobic Z 0 and the right-handed neutrinos opens up a new possibility of searching for these particles simultaneously through the production of Z 0 at the LHC and its decay to a NR pair. We study this process in an inverse seesaw set-up where the heavy neutrinos are pseudo-Dirac in nature. Hence, in our case, the NR pair produce only opposite-sign lepton pairs, as opposed to the Majorana-type neutrinos, which can produce both the same and the oppositesign lepton pairs. In particular, the signature we study involves a same-flavour-opposite-sign lepton pair plus hadronically-decaying boosted W bosons. Our analysis shows that the High Luminosity LHC can discover a TeV-scale leptophobic Z 0 decaying via NR pair for a wide range of available parameters in our model. Considerable parameter regions beyond the reach of the future dijet resonance searches can be probed through our channel.

Abstract

TeV-scale vector-like quarks (VLQs) are an essential ingredient of many new physics models. Because of their vectorlike nature, they do not contribute to the gauge anomalies and are less restricted than their chiral counterparts by the current experimental data. Ones that couple with the thirdgeneration quarks (top and bottom partners, we shall collectively refer to them as top partners) appear in composite Higgs models with a partially-composite top quark [1– 6], extra-dimensional models [7–11], Little-Higgs models [12–15], etc. However, in the last few years, an extensive direct search program at the LHC has gradually tightened the mass bounds on these quarks. For top partners like the T quark (with electromagnetic charge 2/3) or the B quark (with charge −1/3), the current exclusion limit stands as high as ∼ 1.5 TeV [16–20]. The direct VLQ searches generally assume that they decay exclusively to Standard Model (SM) particles, i.e., to a third-generation quark and a heavy vector-boson or a Higgs. However, this assumption need not hold in general, especially if one looks beyond the minimal models where the top partners can have new decay modes. For example, a top partner can decay to another heavy quark or a new boson [11, 21–43]. A possibility that has attracted some interest in the current literature is that a vector-like top partner decays to a new spinless state singlet under the SM gauge group [i.e., (1, 1, 0) under SU(3)c×SU(2)L ×U(1)Y ] and a third-generation quark. The singlet state could be

Abstract

Periodic pattern mining is an emerging technique for knowledge discovery. Most previous approaches have aimed to find only those patterns that exhibit full (or perfect) periodic behavior in databases. Consequently, the existing approaches miss interesting patterns that exhibit partial periodic behavior in a database. With this motivation, this paper proposes a novel model for finding partial periodic patterns that may exist in temporal databases. An efficient pattern-growth algorithm, called Partial Periodic Pattern-growth (3P-growth), is also presented, which can effectively find all desired patterns within a database. Substantial experiments on both real-world and synthetic databases showed that our algorithm is not only efficient in terms of memory and runtime, but is also highly scalable. Finally, the effectiveness of our patterns is demonstrated using two case studies. In the first case study, our model was employed to identify the highly polluted areas in Japan. In the second case study, our model was employed to identify the road segments on which people regularly face traffic congestion.

Abstract

The Securities and Exchange Board of India is the regulatory body for securities and commodity market in India. A growing number of SEBI documents ranging from government regulations to legal case files are now available in the digital form. Advances in natural language processing and machine learning provide opportunities for extracting semantic insights from these documents. We present here a system that performs semantic processing of SEBI documents using state-of-the-art language models to produce enriched regulations containing timelines of amendments and cross references to legal case files.

Abstract

The Securities and Exchange Board of India (SEBI) is the regulatory body for securities and commodities in India. SEBI creates, and enforces regulations that must be followed by all listed companies. To the best of our knowledge, this is the first work on identifying the regulation (s) that a SEBI-related case violates, which could be of substantial value to companies, lawyers, and other stakeholders in the regulatory process. We create a dataset for this task by automatically extracting violations from publicly available case-files. Using this data, we explore various multi-label text classification methods to determine the potentially multiple regulations violated by (the facts of) a case. Our experiments demonstrate the importance of employing contextual text representations to understand complex financial and legal concepts. We also highlight the challenges that must be addressed to develop a fully functional system in the real-world.

Abstract

Several popular Transformer based language models have been found to be successful for text-driven brain encoding. However, existing literature leverages only pretrained text Transformer models and has not explored the efficacy of task-specific learned Transformer representations. In this work, we explore transfer learning from representations learned for ten popular natural language processing tasks (two syntactic and eight semantic) for predicting brain responses from two diverse datasets: Pereira (subjects reading sentences from paragraphs) and Narratives (subjects listening to the spoken stories). Encoding models based on task features are used to predict activity in different regions across the whole brain. Features from coreference resolution, NER, and shallow syntax parsing explain greater variance for the reading activity. On the other hand, for the listening activity, tasks such as paraphrase generation, summarization, and natural language inference show better encoding performance. Experiments across all 10 task representations provide the following cognitive insights: (i) language left hemisphere has higher predictive brain activity versus language right hemisphere, (ii) posterior medial cortex, temporoparieto-occipital junction, dorsal frontal lobe have higher correlation versus early auditory and auditory association cortex, (iii) syntactic and semantic tasks display a good predictive performance across brain region

Abstract

How the brain captures the meaning of linguistic stimuli across multiple views is still a critical open question in neuroscience. Consider three different views of the concept apartment: (1) picture (WP) presented with the target word label, (2) sentence (S) using the target word, and (3) word cloud (WC) containing the target word along with other semantically related words. Unlike previous efforts, which focus only on single view analysis, in this paper, we study the effectiveness of brain decoding in a zero-shot cross-view learning setup. Further, we propose brain decoding in the novel context of cross-view-translation tasks like image captioning (IC), image tagging (IT), keyword extraction (KE), and sentence formation (SF). Using extensive experiments, we demonstrate that cross-view zero-shot brain decoding is practical leading to ∼0.68 average pairwise accuracy across view pairs. Also, the decoded representations are sufficiently detailed to enable high accuracy for cross-view-translation tasks with following pairwise accuracy: IC (78.0), IT (83.0), KE (83.7) and SF (74.5).

Abstract

Enabling effective brain-computer interfaces requires understanding how the human brain encodes stimuli across modalities such as visual, language (or text), etc. Brain encoding aims at constructing fMRI brain activity given a stimulus. There exists a plethora of neural encoding models which study brain encoding for single mode stimuli: visual (pretrained CNNs) or text (pretrained language models). Few recent papers have also obtained separate visual and text representation models and performed late-fusion using simple heuristics. However, previous work has failed to explore: (a) the effectiveness of image Transformer models for encoding visual stimuli, and (b) co-attentive multi-modal modeling for visual and text reasoning. In this paper, we systematically explore the efficacy of image Transformers (ViT, DEiT, and BEiT) and multi-modal Transformers (VisualBERT, LXMERT, and CLIP) for brain encoding. Extensive experiments on two popular datasets, BOLD5000 and Pereira, provide the following insights. (1) To the best of our knowledge, we are the first to investigate the effectiveness of image and multi-modal Transformers for brain encoding. (2) We find that VisualBERT, a multi-modal Transformer, significantly outperforms previously proposed single-mode CNNs, image Transformers as well as other previously proposed multi-modal models, thereby establishing new state-of-theart. The supremacy of visio-linguistic models raises the question of whether the responses elicited in the visual regions are affected implicitly by linguistic processing even when passively viewing images. Future fMRI tasks can verify this computational insight in an appropriate experimental setting.