Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Summary Background Since December, 2019, Wuhan, China, has experienced an outbreak of coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Epidemiological and clinical characteristics of patients with COVID-19 have been reported but risk factors for mortality and a detailed clinical course of illness, including viral shedding, have not been well described. Methods In this retrospective, multicentre cohort study, we included all adult inpatients (≥18 years old) with laboratory-confirmed COVID-19 from Jinyintan Hospital and Wuhan Pulmonary Hospital (Wuhan, China) who had been discharged or had died by Jan 31, 2020. Demographic, clinical, treatment, and laboratory data, including serial samples for viral RNA detection, were extracted from electronic medical records and compared between survivors and non-survivors. We used univariable and multivariable logistic regression methods to explore the risk factors associated with in-hospital death. Findings 191 patients (135 from Jinyintan Hospital and 56 from Wuhan Pulmonary Hospital) were included in this study, of whom 137 were discharged and 54 died in hospital. 91 (48%) patients had a comorbidity, with hypertension being the most common (58 [30%] patients), followed by diabetes (36 [19%] patients) and coronary heart disease (15 [8%] patients). Multivariable regression showed increasing odds of in-hospital death associated with older age (odds ratio 1·10, 95% CI 1·03–1·17, per year increase; p=0·0043), higher Sequential Organ Failure Assessment (SOFA) score (5·65, 2·61–12·23; p Interpretation The potential risk factors of older age, high SOFA score, and d-dimer greater than 1 μg/mL could help clinicians to identify patients with poor prognosis at an early stage. Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future. Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences; National Science Grant for Distinguished Young Scholars; National Key Research and Development Program of China; The Beijing Science and Technology Project; and Major Projects of National Science and Technology on New Drug Creation and Development.

Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Deep Convolutional Neural Network (CNN) is a special type of Neural Networks, which has shown exemplary performance on several competitions related to Computer Vision and Image Processing. Some of the exciting application areas of CNN include Image Classification and Segmentation, Object Detection, Video Processing, Natural Language Processing, and Speech Recognition. The powerful learning ability of deep CNN is primarily due to the use of multiple feature extraction stages that can automatically learn representations from the data. The availability of a large amount of data and improvement in the hardware technology has accelerated the research in CNNs, and recently interesting deep CNN architectures have been reported. Several inspiring ideas to bring advancements in CNNs have been explored, such as the use of different activation and loss functions, parameter optimization, regularization, and architectural innovations. However, the significant improvement in the representational capacity of the deep CNN is achieved through architectural innovations. Notably, the ideas of exploiting spatial and channel information, depth and width of architecture, and multi-path information processing have gained substantial attention. Similarly, the idea of using a block of layers as a structural unit is also gaining popularity. This survey thus focuses on the intrinsic taxonomy present in the recently reported deep CNN architectures and, consequently, classifies the recent innovations in CNN architectures into seven different categories. These seven categories are based on spatial exploitation, depth, multi-path, width, feature-map exploitation, channel boosting, and attention. Additionally, the elementary understanding of CNN components, current challenges, and applications of CNN are also provided.

https://link.springer.com/content/pdf/10.1007/s10462-020-09825-6.pdf

A survey of the recent architectures of deep convolutional neural networks


The relative contributions of cyclonic disturbances (CDs; i.e., low pressure systems, depressions, and cyclonic storms) and non-CDs to annual and seasonal rainfall are studied using 22 years of TRMM and GPM measurements during the passage of 866 CDs in the South Asia region (SAR). The changes in stratiform and convective precipitation within the cyclonic storm and in different CDs are also examined. The rainfall in the wettest regions of the SAR, the west coasts of India and Myanmar, and the slopes of the Himalayas is of non-CD origin, while CD rainfall peaks in the eastern parts of the monsoon trough and the northern Bay of Bengal (BOB). The CD rain fraction (RF) of annual and seasonal rainfall exhibits large spatial variation in the range of 4%–55%. The land–ocean dichotomy exhibited by CD RF is not uniform across India. Large CD RF is confined to the coast in some regions due to topographical barriers, but extends to 800–1000 km inland from the coast in the monsoon trough region. Low pressure systems contribute more to annual rain than depressions and cyclonic storms in the monsoon trough and the northern BOB (∼40%), particularly during the monsoon, mainly due to their frequent occurrence. The stratiform RF and occurrence are higher in CDs than in non-CDs, with the greatest contribution in central India (>80%), whereas the non-CDs are characterized by having higher convective RFs. The stratiform rain occurrence increases with intensification of CDs over both land and ocean, indicating its importance in the intensification of CDs and organizing large-scale systems.

Precipitation Characteristics of Cyclonic Disturbances over the South Asia Region as Revealed by TRMM and GPM

Objective: The plant Cannabis indica is a very popular and well known plant across the globe since thousands of years. In India also it is even more popular as bhang or marijuna from ancient time. A quite descriptions of this plant is written in various ancient books like the granths, vedas, puranas, ayurvedic books, dravyaguna, etc.. Number of medicinal properties have been described for different parts of the plant like flower buds(Ganja), Leaf(Bhang) & Leaf wax(Charas). All the parts of this plant have potent and complex psychotropic properties along with some additional therapeutic actions on different body systems. Here we have fond some opportunities to evaluate herbal extracts of leaves for having aphrodisiac potential. Method: The aphrodisiac activity of Cannabis indicaleaf extracts (Pet.ether, methenol & aqueous) were evaluated in male albino rats. Extracts were administered at a dose of 150mg/kg body weight. At a interval of 0,7,14,21 & 28 day several sexual behavior parameters were determined. At the end serum testosterone and FSH level were also determined. Results: This study also contributes to the pharmacology of aphrodisiacs as the plant Cannabis indica leaf extracts has significant effects on sexual physiology. It has shown effects on sexual behaviors as well as significant change in gonadotropin hormone labels in animal blood serum. Conclusion: This study provides a strong experimental evidence for its aphrodisiac use.

/pdf/pharmacological-evaluation-of-cannabis-indica-for-their-1942zo54hj.pdf

Pharmacological Evaluation of Cannabis indica For Their Aphrodisiac Potential

Four new Cu(II)-based hexagonal complexes with the metallomacrocycle formulae [Cu6(5-nip)6(3-py)6(H2O)12] (1), [Cu6(5-nip)6(3-Clpy)6(H2O)12] (2), [Cu6(5-nip)6(3-Brpy)6(H2O)12] (3), and [Cu6(5-nip)6(3-Ipy)6(H2O)12] (4) have been synthesized using 5-nitroisophthalic acid (H25-nip) and pyridine (py)/3-halopyridine (3-Xpy; X = Cl, Br, and I) ligands. The structural features and supramolecular interactions of compounds 1-4 have been investigated using the single-crystal X-ray diffraction (SCXRD) technique. Interestingly, the hexagonal complexes undergo hydrogen bonding and π···π stacking interactions to form fascinating two-dimensional (2D) honeycomb-like structures. The synthesized complexes exhibit high electrical conductivity, arising from charge transport through space via π···π contacts. However, complexes containing 3-Brpy (3) and 3-Ipy (4) exhibit photosensitivity due to the presence of halogens with a larger size and lower ionization energy. The conductivity results are also in accordance with the theoretical prediction calculated by density functional theory (DFT) study.

Cu(II)-Based Molecular Hexagons Forming Honeycomb-like Networks Exhibit High Electrical Conductivity.

Cognitive state assessment can be effectively performed using Electroencephalogram (EEG). However, due to the curse of dimensionality issues of EEG, most of the clustering methods often lead to poor performance. Deep neural network-based representation learning transforms high-dimensional data into lower-dimensional feature space, increasing the clustering performance. This paper proposes an efficient multimodal (spectral-temporal) deep clustering model to evaluate workload levels from multiple stimuli (visual and auditory)-based n-back task. The proposed model extracts the temporal and spectral EEG features from sequence-wise EEG signal and spectral power. The combined spectral-temporal low-dimensional latent feature is passed to the sparse subspace clustering (SSC) model to estimate different workload levels. The temporal and spectral latent features are learned using the Long short-term memory (LSTM) and Convolutional Neural Network (CNN)-based variational autoencoder (VAE) model. In the SSC method, the collection of data points that lies in the union of low-dimensional subspaces forms a cluster. Here, each cluster overcomes the effect of the outliers from subspace, improving the cluster quality. The proposed model achieves the best clustering accuracy of 98.2% in the subject-independent test and a mean clustering accuracy of 95.2%. The proposed model achieves a significant improvement over the state-of-the-art studies. The effectiveness of the model is also evaluated on two other publicly available n-back datasets. The proposed model enhances the future scope of the deep representation learning-based clustering approach for other cognitive tasks.

Partha Pratim Roy

Papers

Precipitation Characteristics of Cyclonic Disturbances over the South Asia Region as Revealed by TRMM and GPM

Pharmacological Evaluation of Cannabis indica For Their Aphrodisiac Potential

Cu(II)-Based Molecular Hexagons Forming Honeycomb-like Networks Exhibit High Electrical Conductivity.

Multimodal Deep Sparse Subspace Clustering for Multiple Stimuli-based Cognitive task

Mononuclear Nickel and Copper Complexes as Electrocatalyst for Generation of Hydrogen from Acetic Acid