SRI Blog

    It's a bit late but not least to continue my journey of learning. As the new year celebrations are settling down and on the occasion of my birthday, I would like to Recapitulate (Summarise 2020 year) my ML Learning journey. We've looked at 27 different papers, I learned a ton! I hope you found something you enjoyed in the paper selections as well. Here’s a small selection of my personal highlights from the term, in case you missed any of them (in the order in which they originally appeared on the blog) few articles are interlinked on concepts such as Psycho-Linguistics Crypto-Oriented Data Security Psycho-Linguistics Part 1 Psycho-Linguistics Part 2 Machine Unlearning Fragrance Graph- quantitative structure-odor relationship (QSOR) Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic Voice Privacy  Client2Vec: Generic Clients repository for Banking Apps. WAV2SHAPE: Hearing the Shape of a Drum machine I will be topping up my reading lists and getting read...

 -By Google Research {jesseengel,hanoih,gcj,adarob}@google.com Paper Link Code Demo Abstract Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is generated and perceived. A third approach (vocoders/synthesizers) successfully incorporates strong domain knowledge of signal processing and perception, but has been less actively researched due to limited expressivity and difficulty integrating with modern auto-differentiation-based machine learning methods. In this paper, we introduce the Differentiable Digital Signal Processing (DDSP) library, which enables direct integration of classic signal processing elements with deep learning methods. Focusing on audio synthesis, we achieve high-fidelity generation without the need for large autoregressive models or adversarial losses, demonstrating that DDSP enable...

 -By Hugh Leather - University of Edinburgh Edinburgh,                                                   Chris Cummins -  Facebook AI Research Paper Link   image Courtesy:Embecosm Abstract Writing optimising compilers is difficult. The range of programs that may be presented to the compiler is huge and the systems on which they run are complex, heterogeneous, non-deterministic, and constantly changing. The space of possible optimisations is also vast, making it very hard for compiler writers to design heuristics that take all of these considerations into account. As a result, many compiler optimisations are out of date or poorly tuned. A retrospective of machine learning in compiler optimisation from its earliest inception, through some of the works that set themselves apart, to today’s deep learning, finishing with our visi...

 -By Hayata Yamasaki,  Sathyawageeswar Subramanian,  Sho Sonoda,  Masato Koashi Paper Link image Courtesy: Fossguru.com Abstract Kernel methods augmented with random features give scalable algorithms for learning from big data. But it has been computationally hard to sample random features according to a probability distribution that is optimized for the data, so as to minimize the required number of features for achieving the learning to the desired accuracy. Here, we develop a quantum algorithm for sampling from this optimized distribution over features, in runtime O(D) that is linear in the dimension D of the input data. Our algorithm achieves an exponential speedup in D compared to any known classical algorithm for this sampling task. In contrast to existing quantum machine learning algorithms, our algorithm circumvents sparsity and low-rank assumptions and thus has wide applicability. We also show that the sampled features can be combined with regression by...

 He guo, Xiameng Qin, Jiaming Liu, Junyu Han, Jingtuo Liu, Errui Ding Department of Computer Vision Technology(VIS), Baidu Inc Paper link Abstract Extracting entity from images is a crucial part of many OCR applications, such as entity recognition of cards, invoices, and receipts. Most of the existing works employ classical detection and recognition paradigm. Paper proposes an Entity-aware Attention Text Extraction Network called EATEN , which is an end-to-end trainable system to extract the entities without any post-processing. In the proposed framework, each entity is parsed by its corresponding entity-aware decoder, respectively. Moreover, we innovatively introduce a state transition mechanism which further improves the robustness of entity extraction. In consideration of the absence of public benchmarks, we construct a dataset of almost 0.6 million images in three realworld scenarios (train ticket, passport and business card), which is publicly available at https://github.com/b...

- By Anatasiia Kornilova , Mikhail Salnikov, Olga Novitskaya, Maria Begicheva, Egor Sevriugov, Kirill Shcherbakov  Paper Link Github Code Abstract  In the last decade, a huge step was done in the field of mobile microscopes development as well as in the field of mobile microscopy application to real-life disease diagnostics and a lot of other important areas (air/water quality pollution, education, agriculture). In the current study, we applied image processing techniques from Deep Learning (in-focus/out-of-focus classification, image deblurring and denoising, multi-focus image fusion) to the data obtained from the mobile microscope. Overview of significant works for every the task is presented, the most suitable approaches were highlighted. With the development of optical microscopy technologies, the cost of simple microscopes has become low enough for their mass usage. A considerable role in that class plays mobile microscopy – the field where smartphone camera and computati...

-By Han Han, Vincent Lostanlen  New York University Paper Link ABSTRACT  Disentangling and recovering physical attributes, such as shape and material, from a few waveform examples is a challenging inverse problem in audio signal processing, with numerous applications in musical acoustics as well as structural engineering. We propose to address this problem via a combination of time–frequency analysis and supervised machine learning. We start by synthesizing a dataset of sounds using the functional transformation method. Then, we represent each percussive sound in terms of its time-invariant scattering transform coefficients and formulate the parametric estimation of the resonator as multidimensional regression with a deep convolutional neural network. We interpolate scattering coefficients over the surface of the drum as a surrogate for potentially missing data, and study the response of the neural network to interpolated samples. Lastly, we resynthesize drum sounds ...