Recent methods in speech and language technology pretrain very LARGE models which are fine-tuned for specific tasks. However, the benefits of such LARGE models are often limited to a few resource rich languages of the world. In this work, we make multiple contributions towards building ASR systems for low resource languages from the Indian subcontinent. First, we curate 17,000 hours of raw speech data for 40 Indian languages from a wide variety of domains including education, news, technology, and finance. Second, using this raw speech data we pretrain several variants of wav2vec style models for 40 Indian languages. Third, we analyze the pretrained models to find key features: codebook vectors of similar sounding phonemes are shared across languages, representations across layers are discriminative of the language family, and attention heads often pay attention within small local windows. Fourth, we fine-tune this model for downstream ASR for 9 languages and obtain state-of-the-art results on 3 public datasets, including on very low-resource languages such as Sinhala and Nepali. Our work establishes that multilingual pretraining is an effective strategy for building ASR systems for the linguistically diverse speakers of the Indian subcontinent. Our code, data and models are available publicly at https://indicnlp.ai4bharat.org/indicwav2vec/ and we hope they will help advance research in ASR for Indic languages.

In this paper we use The Quijote simulations in order to extract the cosmological parameters through Bayesian Neural Networks. This kind of models has a remarkable ability of estimating the associated uncertainty, which is one of the ultimate goals in the precision cosmology era. We demonstrate the advantages of BNNs for extracting more complex output distributions and non-Gaussianities information from the simulations.

Variational inference is a powerful paradigm for approximate Bayesian inference with a number of appealing properties, including support for model learning and data subsampling. By contrast MCMC methods like Hamiltonian Monte Carlo do not share these properties but remain attractive since, contrary to parametric methods, MCMC is asymptotically unbiased. For these reasons researchers have sought to combine the strengths of both classes of algorithms, with recent approaches coming closer to realizing this vision in practice. However, supporting data subsampling in these hybrid methods can be a challenge, a shortcoming that we address by introducing a surrogate likelihood that can be learned jointly with other variational parameters. We argue theoretically that the resulting algorithm permits the user to make an intuitive trade-off between inference fidelity and computational cost. In an extensive empirical comparison we show that our method performs well in practice and that it is well-suited for black-box inference in probabilistic programming frameworks.

Development of the new methods of surface water observation is crucial in the perspective of increasingly frequent extreme hydrological events related to global warming and increasing demand for water. Orthophotos and digital surface models (DSMs) obtained using UAV photogrammetry can be used to determine the Water Surface Elevation (WSE) of a river. However, this task is difficult due to disturbances of the water surface on DSMs caused by limitations of photogrammetric algorithms. In this study, machine learning was used to extract a WSE value from disturbed photogrammetric data. A brand new dataset has been prepared specifically for this purpose by hydrology and photogrammetry experts. The new method is an important step toward automating water surface level measurements with high spatial and temporal resolution. Such data can be used to validate and calibrate of hydrological, hydraulic and hydrodynamic models making hydrological forecasts more accurate, in particular predicting extreme and dangerous events such as floods or droughts. For our knowledge this is the first approach in which dataset was created for this purpose and deep learning models were used for this task. Additionally, neuroevolution algorithm was set to explore different architectures to find local optimal models and non-gradient search was performed to fine-tune the model parameters. The achieved results have better accuracy compared to manual methods of determining WSE from photogrammetric DSMs.

The malware has been being one of the most damaging threats to computers that span across multiple operating systems and various file formats. To defend against the ever-increasing and ever-evolving threats of malware, tremendous efforts have been made to propose a variety of malware detection methods that attempt to effectively and efficiently detect malware. Recent studies have shown that, on the one hand, existing ML and DL enable the superior detection of newly emerging and previously unseen malware. However, on the other hand, ML and DL models are inherently vulnerable to adversarial attacks in the form of adversarial examples, which are maliciously generated by slightly and carefully perturbing the legitimate inputs to confuse the targeted models. Basically, adversarial attacks are initially extensively studied in the domain of computer vision, and some quickly expanded to other domains, including NLP, speech recognition and even malware detection. In this paper, we focus on malware with the file format of portable executable (PE) in the family of Windows operating systems, namely Windows PE malware, as a representative case to study the adversarial attack methods in such adversarial settings. To be specific, we start by first outlining the general learning framework of Windows PE malware detection based on ML/DL and subsequently highlighting three unique challenges of performing adversarial attacks in the context of PE malware. We then conduct a comprehensive and systematic review to categorize the state-of-the-art adversarial attacks against PE malware detection, as well as corresponding defenses to increase the robustness of PE malware detection. We conclude the paper by first presenting other related attacks against Windows PE malware detection beyond the adversarial attacks and then shedding light on future research directions and opportunities.

When mining large datasets in order to predict new data, limitations of the principles behind statistical machine learning pose a serious challenge not only to the Big Data deluge, but also to the traditional assumptions that data generating processes are biased toward low algorithmic complexity. Even when one assumes an underlying algorithmic-informational bias toward simplicity in finite dataset generators, we show that fully automated, with or without access to pseudo-random generators, computable learning algorithms, in particular those of statistical nature used in current approaches to machine learning (including deep learning), can always be deceived, naturally or artificially, by sufficiently large datasets. In particular, we demonstrate that, for every finite learning algorithm, there is a sufficiently large dataset size above which the algorithmic probability of an unpredictable deceiver is an upper bound (up to a multiplicative constant that only depends on the learning algorithm) for the algorithmic probability of any other larger dataset. In other words, very large and complex datasets are as likely to deceive learning algorithms into a "simplicity bubble" as any other particular dataset. These deceiving datasets guarantee that any prediction will diverge from the high-algorithmic-complexity globally optimal solution while converging toward the low-algorithmic-complexity locally optimal solution. We discuss the framework and empirical conditions for circumventing this deceptive phenomenon, moving away from statistical machine learning towards a stronger type of machine learning based on, or motivated by, the intrinsic power of algorithmic information theory and computability theory.

The Query Focused Text Summarization (QFTS) task aims at building systems that generate the summary of the text document(s) based on the given query. A key challenge in addressing this task is the lack of large labeled data for training the summarization model. In this paper, we address this challenge by exploring a series of domain adaptation techniques. Given the recent success of pre-trained transformer models in a wide range of natural language processing tasks, we utilize such models to generate abstractive summaries for the QFTS task for both single-document and multi-document scenarios. For domain adaptation, we apply a variety of techniques using pre-trained transformer-based summarization models including transfer learning, weakly supervised learning, and distant supervision. Extensive experiments on six datasets show that our proposed approach is very effective in generating abstractive summaries for the QFTS task while setting a new state-of-the-art result in several datasets across a set of automatic and human evaluation metrics.

What comes to mind when we imagine a cutting-edge, tech-savvy workplace? But recent advances in technology, especially Artificial Intelligence, have attracted them too. AI-based tools have the ability to parse an unlimited amount of data, recognise patterns and apply them to new information. This allows legislators to have a dialogue with large constituents, analyse diverse opinions, participate remotely in plenary and committee meetings, and reduce paperwork through digitisation. Where is India in this picture?

The Resource Allocation approach (RA) improves the performance of MOEA/D by maintaining a big population and updating few solutions each generation. However, most of the studies on RA generally focused on the properties of different Resource Allocation metrics. Thus, it is still uncertain what the main factors are that lead to increments in performance of MOEA/D with RA. This study investigates the effects of MOEA/D with the Partial Update Strategy in an extensive set of MOPs to generate insights into correspondences of MOEA/D with the Partial Update and MOEA/D with small population size and big population size. Our work undertakes an in-depth analysis of the populational dynamics behaviour considering their final approximation Pareto sets, anytime hypervolume performance, attained regions and number of unique non-dominated solutions. Our results indicate that MOEA/D with Partial Update progresses with the search as fast as MOEA/D with small population size and explores the search space as MOEA/D with big population size. MOEA/D with Partial Update can mitigate common problems related to population size choice with better convergence speed in most MOPs, as shown by the results of hypervolume and number of unique non-dominated solutions, the anytime performance and Empirical Attainment Function indicates.

As one of the most prevalent neurodegenerative disorders, Parkinson's disease (PD) has a significant impact on the fine motor skills of patients. The complex interplay of different articulators during speech production and realization of required muscle tension become increasingly difficult, thus leading to a dysarthric speech. Characteristic patterns such as vowel instability, slurred pronunciation and slow speech can often be observed in the affected individuals and were analyzed in previous studies to determine the presence and progression of PD. In this work, we used a phonetic recognizer trained exclusively on healthy speech data to investigate how PD affected the phonetic footprint of patients. We rediscovered numerous patterns that had been described in previous contributions although our system had never seen any pathological speech previously. Furthermore, we could show that intermediate activations from the neural network could serve as feature vectors encoding information related to the disease state of individuals. We were also able to directly correlate the expert-rated intelligibility of a speaker with the mean confidence of phonetic predictions. Our results support the assumption that pathological data is not necessarily required to train systems that are capable of analyzing PD speech.