lear

Budget 2020: FM makes entrepreneurs' lives easier with new investment clearance cell

The Department for Promotion of Industry and Internal Trade (DPIIT) plans to set up an investment clearance cell for applying for licences and incentives given by both central and state governments. Separately, it is also looking at developing a single application form for all kinds of clearances and deemed approvals.




lear

Should a small business invest in AI and machine learning software?

Both AI and ML are touted to give businesses the edge they need, improve efficiencies, make sales and marketing better and even help in critical HR functions.




lear

AI, machine learning can help achieve $5 trillion target: Piyush Goyal

“Our government believes artificial intelligence, in different forms, can help us achieve the $5 trillion benchmark over the next five years, but also help us do it effectively and efficiently,” Goyal said while inaugurating the NSE Knowledge Hub here. The hub is an AI-powered learning ecosystem for the banking, financial services and insurance sector.




lear

SCCM Pod-266 Autologous Bone Marrow Mononuclear Cells Reduce Therapeutic Intensity for Severe TBI in Children

Margaret Parker, MD, MCCM, speaks with George P. Liao, MD and Charles S. Cox, MD




lear

Indian students with foreign degrees returning home: Lessons India can learn from China

High costs, poor job prospects and wrangles over work permits are persuading a host of Indian students with foreign degrees to return home.




lear

Growth or Re-investment or Payout? Clear the confusion

Take a marathon for instance; while one runner may have a calculative approach, another might count on his unmatched stamina to run for miles together without stopping - but both could be champions in the same sport, just that their approach is different.




lear

Asymptomatic Indians cleared by UAE health authorities only to fly back home from Thursday: Embassy

The Indian nationals cleared by the UAE health authorities and found to be asymptomatic will only be allowed to fly back home in one of India's biggest ever repatriation exercises, the Indian Embassy in Abu Dhabi has said ahead of the first set of flights on Thursday.




lear

China needs more nuclear warheads: Global Times editor

The Global Times is published by the People's Daily, the official newspaper of China's ruling Communist Party. The party has been known to float ideas and guide public sentiments via the Global Times, which tends to take a nationalistic stance on issues involving other countries.




lear

Move Along: Psyllium And Epsom Salt Clear Sand From Equine Intestines

Sand colic in horses occurs when sand accumulates in the large colon. Occurring around the world, sand colic is often treated by a veterinarian, but preventative measures are available, including adding psyllium to the horse's feed. A bulk-forming laxative that absorbs water, psyllium can pass through the digestive system without being completely dissolved. Magnesium sulphate, […]

The post Move Along: Psyllium And Epsom Salt Clear Sand From Equine Intestines appeared first on Horse Racing News | Paulick Report.




lear

Laplace’s Demon: A Seminar Series about Bayesian Machine Learning at Scale

David Rohde points us to this new seminar series that has the following description: Machine learning is changing the world we live in at a break neck pace. From image recognition and generation, to the deployment of recommender systems, it seems to be breaking new ground constantly and influencing almost every aspect of our lives. […]




lear

Parx Has Several Hurdles To Clear Before Racing Can Resume

There is no firm timeline in place for the resumption of racing at Parx, but when it does happen, it's going to look quite different. That's the word from Sal DeBunda, president of the Pennsylvania Thoroughbred Horsemen's Association in a video update posted on the group's Facebook page last week. DeBunda explained that Pennsylvania Gov. […]

The post Parx Has Several Hurdles To Clear Before Racing Can Resume appeared first on Horse Racing News | Paulick Report.




lear

Desert View Drive in Grand Canyon National Park is Closed as Rangers Clear Multiple Accidents

Grand Canyon National Park rangers and road crews continue to work on clearing Desert View Drive of multiple accidents after light snow fell on wet roads just as evening temperatures dropped below freezing on Tuesday, December 29. https://www.nps.gov/grca/learn/news/2009-12-29_accidents.htm




lear

Grand Canyon National Park to Temporarily Close North Kaibab Trail and Restrict Rim-to-Rim Traffic while Crews Clear Rockslide Debris; Ribbon Falls also Closed

On Monday, March 27, Grand Canyon National Park will begin daily closures of the North Kaibab Trail at Redwall Bridge to remove debris from a storm-caused rockslide. During this time, rim-to-rim travel will be restricted. https://www.nps.gov/grca/learn/news/north-kaibab-ribbons-falls-temporary-closures.htm




lear

Gold Coast clears passage for superyachts

INTERNATIONAL superyachts can sail into the Gold Coast Seaway permanently in a coup for the Gold Coast boating and tourism industries, with approval secured for a clearing station.




lear

A Clear Picture of Smoke: Bluesky Smoke Forecasting

Over the last several decades, the overall air quality goal in the United States has been to protect public health and clear skies by reducing emissions. At the same time, however, the risk of catastrophic fire has been rising in forests around the country as overly dense trees and understory brush crowd the stands.




lear

Learning To Manage A Complex Ecosystem: Adaptive Management and The Northwest Forest Plan

The Northwest Forest Plan (the Plan) identifies adaptive management as a central strategy for effective implementation. Despite this, there has been a lack of any systematic evaluation of its performance.




lear

Socioeconomic assessment of Forest Service American Recovery and Reinvestment Act projects: key findings and lessons learned.

The American Recovery and Reinvestment Act of 2009 (the Recovery Act) aimed to create jobs and promote economic growth while addressing the Nation's social and environmental needs. The USDA Forest Service received $1.15 billion in economic recovery funding. This report contains key findings and lessons learned from a socioeconomic assessment of Forest Service Recovery Act projects. The assessment examines how Forest Service economic recovery projects at eight case-study locations around the United States are contributing to socioeconomic well-being in rural counties affected by the economic recession of 2007-2009. It also investigates how Forest Service mission-related work can be accomplished in a manner that creates local community development opportunities. This report is a companion to general technical report PNW-GTR-831, which contains the full case-study reports.




lear

Relations of native and exotic species 5 years after clearcutting with and without herbicide and logging debris treatments

To increase timber production and manage other forest resource values, some land managers have undertaken logging debris and vegetation control treatments after forest harvest. We explored the roles of clearcutting on plant community composition and structure at three sites where logging debris was dispersed, piled, or removed and vegetation was annually treated or not treated with herbicides for 5 years. Without vegetation control, a competitive relation was identified between exotic and native ruderal (i.e., disturbance-associated) species. When exotic ruderal cover changed by 4 percent, native ruderal cover changed by 10 percent in the opposite direction. This relation was independent of site, but site was important in determining the overall dominance of ruderals. Five annual vegetation control treatments increased Douglas-fir (Pseudotsuga menziesii (Mirb.) Franco) growth, but decreased richness and cover of other species at the rate of one species per 10 percent reduction in cover. Debris treatment effects were small and found on only one site.




lear

Boy who woke up nauseous horrified to learn he had 'ping pong ball sized' tumour

Blyth schoolboy Ryan Office has recently returned from receiving proton beam therapy in Florida after being diagnosed with a very rare brain tumour



  • North East News

lear

WGBH wins Excellence in Early Learning Digital Media Award for the app, 'Molly of Denali'

PHILADELPHIA – WGBH is the 2020 recipient of the Excellence in Early Learning Digital Media Award for the app, Molly of Denali. The award was announced today by the Association for Library Service to Children (ALSC), a division of the American Library Association (ALA), during the ALA Midwinter Meeting & Exhibition held January 24 - 28, in Philadelphia.




lear

5 Critical Lessons Learned Organizing WordCamp Ann Arbor for the Third Time

In early 2014 I had just gotten married and recently moved into a new home. With two major life events out of the way, I decided I was ready to lead a WordCamp. I originally planned to organize WordCamp Detroit. I was an organizer twice before and the event had missed a year and I […]

The post 5 Critical Lessons Learned Organizing WordCamp Ann Arbor for the Third Time appeared first on Psychology of Web Design | 3.7 Blog.




lear

Top 10 Toolkits and Libraries for Deep Learning in 2020

Deep Learning is a branch of artificial intelligence and a subset of machine learning that focuses on networks capable of, usually, unsupervised learning from unstructured and other forms of data. It is also known as deep structured learning or differential programming. Architectures inspired by deep learning find use in a range of fields, such as...




lear

Learning the Basics of Photo Editing

Whether you’re into photography, there are so many basic skills that you can learn when it comes to photo editing that can make a huge difference in your photos and selfies. Between brightening up a photo, changing the size, or cutting something out, there’s always a small thing you wish you could change. In order to do that, you should learn these basic photo editing tools so that you can adjust your photos in the simplest manner. Adobe photoshop If you were to use only one software for photo editing, then it should be none other than Adobe Photoshop. With

The post Learning the Basics of Photo Editing appeared first on Photoshop Lady.




lear

This trip solidified my conviction to learning photography. A...



This trip solidified my conviction to learning photography. A lot has happened since this shot was taken.
Can you pinpoint the moment you decided to pursue photography? (at Toronto, Ontario)




lear

New Branding & Website Design Launched for Enterprise High School in Clearwater, Florida

We recently completed a full rebrand and website design project for Enterprise High School, a charter school located in Clearwater,...continue reading




lear

Should Designers Learn How to Code?

https://thenextweb.com/growth-quarters/2020/05/08/should-designers-learn-how-to-code-syndication/




lear

What I learned from living a socially isolated life for the past two years

“It will get easier after you adjust."After receiving a traumatic brain injury from a car crash two years ago, the Los Angeles-based journalist Amanda Chicago Lewis has lived in social isolation. Because of stay-at-home orders to reduce the spread of COVID-19, more people are now living in similar circumstances. Below, Lewis shares how she’s adapted her apartment, her routine, and her habits to cope with being at home for extended periods of time.




lear

7 Reasons Every Photographer Should Learn How to Use Photoshop

Many photographers think that learning how to find the ideal location and take a picture at the right time is all they need to know. However, this isn’t the case, and in a world where CGI rivals reality and touch-ups via photo editing software are now seen as a necessity to customers, relying on point and click will kill your photography business. Here are seven reasons every photographer should learn how to use Photoshop.   Royalty Free Photo Touch-Ups Are Essential When a family orders school photos, they pay a flat fee for copies of the school pictures and a little more if the child’s name is embossed on the picture. They pay a separate fee if the picture is touched up, whether it is hiding acne or reducing glare on the child’s glasses. Photographers who know how to touch up photos without making it look artificial or cartoonish can ... Read more

The post 7 Reasons Every Photographer Should Learn How to Use Photoshop appeared first on Digital Photography Tutorials.




lear

5 Critical Lessons Learned Organizing WordCamp Ann Arbor for the Third Time

In early 2014 I had just gotten married and recently moved into a new home. With two major life events out of the way, I decided I was ready to lead a WordCamp. I originally planned to organize WordCamp Detroit. I was an organizer twice before and the event had missed a year and I […]

The post 5 Critical Lessons Learned Organizing WordCamp Ann Arbor for the Third Time appeared first on Psychology of Web Design | 3.7 Blog.




lear

Judge Could Hold Up Trump Administration's Bid to Clear Flynn, Legal Experts say

The notoriously independent-minded federal judge who once said he was disgusted by the conduct of Michael Flynn could block the administration's bid to drop criminal charges against the former adviser to President Donald Trump, legal experts said.




lear

Trump Declares, 'I Learned a Lot from Nixon'

During an interview on "Fox and Friends," Trump explained why he chose not to go on a firing spree amid Special Counsel Robert Mueller's Russia investigation a la Nixon's Saturday Night Massacre during the Watergate scandal. "I learned a lot from Richard Nixon: Don't fire people," the President said. "I learned a lot. I study history, and the firing of everybody ... .I should've, in one way," he continued. "But I'm glad I didn't because look at the way it turned out."




lear

Clear elements and clear rings. (arXiv:2005.03387v1 [math.AC])

An element in a ring $R$ is called clear if it is the sum of unit-regular element and unit. An associative ring is clear if every its element is clear. In this paper we defined clear rings and extended many results to wider class. Finally, we proved that a commutative B'ezout domain is an elementary divisor ring if and only if every full matrix order 2 over it is nontrivial clear.




lear

The UCT problem for nuclear $C^ast$-algebras. (arXiv:2005.03184v1 [math.OA])

In recent years, a large class of nuclear $C^ast$-algebras have been classified, modulo an assumption on the Universal Coefficient Theorem (UCT). We think this assumption is redundant and propose a strategy for proving it. Indeed, following the original proof of the classification theorem, we propose bridging the gap between reduction theorems and examples. While many such bridges are possible, various approximate ideal structures appear quite promising.




lear

Modeling nanoconfinement effects using active learning. (arXiv:2005.02587v2 [physics.app-ph] UPDATED)

Predicting the spatial configuration of gas molecules in nanopores of shale formations is crucial for fluid flow forecasting and hydrocarbon reserves estimation. The key challenge in these tight formations is that the majority of the pore sizes are less than 50 nm. At this scale, the fluid properties are affected by nanoconfinement effects due to the increased fluid-solid interactions. For instance, gas adsorption to the pore walls could account for up to 85% of the total hydrocarbon volume in a tight reservoir. Although there are analytical solutions that describe this phenomenon for simple geometries, they are not suitable for describing realistic pores, where surface roughness and geometric anisotropy play important roles. To describe these, molecular dynamics (MD) simulations are used since they consider fluid-solid and fluid-fluid interactions at the molecular level. However, MD simulations are computationally expensive, and are not able to simulate scales larger than a few connected nanopores. We present a method for building and training physics-based deep learning surrogate models to carry out fast and accurate predictions of molecular configurations of gas inside nanopores. Since training deep learning models requires extensive databases that are computationally expensive to create, we employ active learning (AL). AL reduces the overhead of creating comprehensive sets of high-fidelity data by determining where the model uncertainty is greatest, and running simulations on the fly to minimize it. The proposed workflow enables nanoconfinement effects to be rigorously considered at the mesoscale where complex connected sets of nanopores control key applications such as hydrocarbon recovery and CO2 sequestration.




lear

Temporal Event Segmentation using Attention-based Perceptual Prediction Model for Continual Learning. (arXiv:2005.02463v2 [cs.CV] UPDATED)

Temporal event segmentation of a long video into coherent events requires a high level understanding of activities' temporal features. The event segmentation problem has been tackled by researchers in an offline training scheme, either by providing full, or weak, supervision through manually annotated labels or by self-supervised epoch based training. In this work, we present a continual learning perceptual prediction framework (influenced by cognitive psychology) capable of temporal event segmentation through understanding of the underlying representation of objects within individual frames. Our framework also outputs attention maps which effectively localize and track events-causing objects in each frame. The model is tested on a wildlife monitoring dataset in a continual training manner resulting in $80\%$ recall rate at $20\%$ false positive rate for frame level segmentation. Activity level testing has yielded $80\%$ activity recall rate for one false activity detection every 50 minutes.




lear

Differential Machine Learning. (arXiv:2005.02347v2 [q-fin.CP] UPDATED)

Differential machine learning (ML) extends supervised learning, with models trained on examples of not only inputs and labels, but also differentials of labels to inputs.

Differential ML is applicable in all situations where high quality first order derivatives wrt training inputs are available. In the context of financial Derivatives risk management, pathwise differentials are efficiently computed with automatic adjoint differentiation (AAD). Differential ML, combined with AAD, provides extremely effective pricing and risk approximations. We can produce fast pricing analytics in models too complex for closed form solutions, extract the risk factors of complex transactions and trading books, and effectively compute risk management metrics like reports across a large number of scenarios, backtesting and simulation of hedge strategies, or capital regulations.

The article focuses on differential deep learning (DL), arguably the strongest application. Standard DL trains neural networks (NN) on punctual examples, whereas differential DL teaches them the shape of the target function, resulting in vastly improved performance, illustrated with a number of numerical examples, both idealized and real world. In the online appendices, we apply differential learning to other ML models, like classic regression or principal component analysis (PCA), with equally remarkable results.

This paper is meant to be read in conjunction with its companion GitHub repo https://github.com/differential-machine-learning, where we posted a TensorFlow implementation, tested on Google Colab, along with examples from the article and additional ones. We also posted appendices covering many practical implementation details not covered in the paper, mathematical proofs, application to ML models besides neural networks and extensions necessary for a reliable implementation in production.




lear

On-board Deep-learning-based Unmanned Aerial Vehicle Fault Cause Detection and Identification. (arXiv:2005.00336v2 [eess.SP] UPDATED)

With the increase in use of Unmanned Aerial Vehicles (UAVs)/drones, it is important to detect and identify causes of failure in real time for proper recovery from a potential crash-like scenario or post incident forensics analysis. The cause of crash could be either a fault in the sensor/actuator system, a physical damage/attack, or a cyber attack on the drone's software. In this paper, we propose novel architectures based on deep Convolutional and Long Short-Term Memory Neural Networks (CNNs and LSTMs) to detect (via Autoencoder) and classify drone mis-operations based on sensor data. The proposed architectures are able to learn high-level features automatically from the raw sensor data and learn the spatial and temporal dynamics in the sensor data. We validate the proposed deep-learning architectures via simulations and experiments on a real drone. Empirical results show that our solution is able to detect with over 90% accuracy and classify various types of drone mis-operations (with about 99% accuracy (simulation data) and upto 88% accuracy (experimental data)).




lear

Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment. (arXiv:2005.00165v3 [cs.CL] UPDATED)

A standard approach to evaluating language models analyzes how models assign probabilities to valid versus invalid syntactic constructions (i.e. is a grammatical sentence more probable than an ungrammatical sentence). Our work uses ambiguous relative clause attachment to extend such evaluations to cases of multiple simultaneous valid interpretations, where stark grammaticality differences are absent. We compare model performance in English and Spanish to show that non-linguistic biases in RNN LMs advantageously overlap with syntactic structure in English but not Spanish. Thus, English models may appear to acquire human-like syntactic preferences, while models trained on Spanish fail to acquire comparable human-like preferences. We conclude by relating these results to broader concerns about the relationship between comprehension (i.e. typical language model use cases) and production (which generates the training data for language models), suggesting that necessary linguistic biases are not present in the training signal at all.




lear

SPECTER: Document-level Representation Learning using Citation-informed Transformers. (arXiv:2004.07180v3 [cs.CL] UPDATED)

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level training objectives and do not leverage information on inter-document relatedness, which limits their document-level representation power. For applications on scientific documents, such as classification and recommendation, the embeddings power strong performance on end tasks. We propose SPECTER, a new method to generate document-level embedding of scientific documents based on pretraining a Transformer language model on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning. Additionally, to encourage further research on document-level models, we introduce SciDocs, a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation. We show that SPECTER outperforms a variety of competitive baselines on the benchmark.




lear

Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016. (arXiv:2004.06286v3 [cs.HC] UPDATED)

A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. Electroencephalograms (EEGs) used in BCIs are weak, easily contaminated by interference and noise, non-stationary for the same subject, and varying across different subjects and sessions. Therefore, it is difficult to build a generic pattern recognition model in an EEG-based BCI system that is optimal for different subjects, during different sessions, for different devices and tasks. Usually, a calibration session is needed to collect some training data for a new subject, which is time consuming and user unfriendly. Transfer learning (TL), which utilizes data or knowledge from similar or relevant subjects/sessions/devices/tasks to facilitate learning for a new subject/session/device/task, is frequently used to reduce the amount of calibration effort. This paper reviews journal publications on TL approaches in EEG-based BCIs in the last few years, i.e., since 2016. Six paradigms and applications -- motor imagery, event-related potentials, steady-state visual evoked potentials, affective BCIs, regression problems, and adversarial attacks -- are considered. For each paradigm/application, we group the TL approaches into cross-subject/session, cross-device, and cross-task settings and review them separately. Observations and conclusions are made at the end of the paper, which may point to future research directions.




lear

Watching the World Go By: Representation Learning from Unlabeled Videos. (arXiv:2003.07990v2 [cs.CV] UPDATED)

Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of the same image and a large batch of unrelated images. Networks learn to ignore the augmentation noise and extract semantically meaningful representations. Prior work uses artificial data augmentation techniques such as cropping, and color jitter which can only affect the image in superficial ways and are not aligned with how objects actually change e.g. occlusion, deformation, viewpoint change. In this paper, we argue that videos offer this natural augmentation for free. Videos can provide entirely new views of objects, show deformation, and even connect semantically similar but visually distinct concepts. We propose Video Noise Contrastive Estimation, a method for using unlabeled video to learn strong, transferable single image representations. We demonstrate improvements over recent unsupervised single image techniques, as well as over fully supervised ImageNet pretraining, across a variety of temporal and non-temporal tasks. Code and the Random Related Video Views dataset are available at https://www.github.com/danielgordon10/vince




lear

Trees and Forests in Nuclear Physics. (arXiv:2002.10290v2 [nucl-th] UPDATED)

We present a simple introduction to the decision tree algorithm using some examples from nuclear physics. We show how to improve the accuracy of the classical liquid drop nuclear mass model by performing Feature Engineering with a decision tree. Finally, we apply the method to the Duflo-Zuker model showing that, despite their simplicity, decision trees are capable of improving the description of nuclear masses using a limited number of free parameters.




lear

Lake Ice Detection from Sentinel-1 SAR with Deep Learning. (arXiv:2002.07040v2 [eess.IV] UPDATED)

Lake ice, as part of the Essential Climate Variable (ECV) lakes, is an important indicator to monitor climate change and global warming. The spatio-temporal extent of lake ice cover, along with the timings of key phenological events such as freeze-up and break-up, provide important cues about the local and global climate. We present a lake ice monitoring system based on the automatic analysis of Sentinel-1 Synthetic Aperture Radar (SAR) data with a deep neural network. In previous studies that used optical satellite imagery for lake ice monitoring, frequent cloud cover was a main limiting factor, which we overcome thanks to the ability of microwave sensors to penetrate clouds and observe the lakes regardless of the weather and illumination conditions. We cast ice detection as a two class (frozen, non-frozen) semantic segmentation problem and solve it using a state-of-the-art deep convolutional network (CNN). We report results on two winters ( 2016 - 17 and 2017 - 18 ) and three alpine lakes in Switzerland. The proposed model reaches mean Intersection-over-Union (mIoU) scores >90% on average, and >84% even for the most difficult lake. Additionally, we perform cross-validation tests and show that our algorithm generalises well across unseen lakes and winters.




lear

SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval. (arXiv:1912.05891v2 [cs.IR] UPDATED)

In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents. Therefore, an ideal ranking model would be a mapping from a document set to a permutation on the set, and should satisfy two critical requirements: (1)~it should have the ability to model cross-document interactions so as to capture local context information in a query; (2)~it should be permutation-invariant, which means that any permutation of the inputted documents would not change the output ranking. Previous studies on learning-to-rank either design uni-variate scoring functions that score each document separately, and thus failed to model the cross-document interactions; or construct multivariate scoring functions that score documents sequentially, which inevitably sacrifice the permutation invariance requirement. In this paper, we propose a neural learning-to-rank model called SetRank which directly learns a permutation-invariant ranking model defined on document sets of any size. SetRank employs a stack of (induced) multi-head self attention blocks as its key component for learning the embeddings for all of the retrieved documents jointly. The self-attention mechanism not only helps SetRank to capture the local context information from cross-document interactions, but also to learn permutation-equivariant representations for the inputted documents, which therefore achieving a permutation-invariant ranking model. Experimental results on three large scale benchmarks showed that the SetRank significantly outperformed the baselines include the traditional learning-to-rank models and state-of-the-art Neural IR models.




lear

Novel Deep Learning Framework for Wideband Spectrum Characterization at Sub-Nyquist Rate. (arXiv:1912.05255v2 [eess.SP] UPDATED)

Introduction of spectrum-sharing in 5G and subsequent generation networks demand base-station(s) with the capability to characterize the wideband spectrum spanned over licensed, shared and unlicensed non-contiguous frequency bands. Spectrum characterization involves the identification of vacant bands along with center frequency and parameters (energy, modulation, etc.) of occupied bands. Such characterization at Nyquist sampling is area and power-hungry due to the need for high-speed digitization. Though sub-Nyquist sampling (SNS) offers an excellent alternative when the spectrum is sparse, it suffers from poor performance at low signal to noise ratio (SNR) and demands careful design and integration of digital reconstruction, tunable channelizer and characterization algorithms. In this paper, we propose a novel deep-learning framework via a single unified pipeline to accomplish two tasks: 1)~Reconstruct the signal directly from sub-Nyquist samples, and 2)~Wideband spectrum characterization. The proposed approach eliminates the need for complex signal conditioning between reconstruction and characterization and does not need complex tunable channelizers. We extensively compare the performance of our framework for a wide range of modulation schemes, SNR and channel conditions. We show that the proposed framework outperforms existing SNS based approaches and characterization performance approaches to Nyquist sampling-based framework with an increase in SNR. Easy to design and integrate along with a single unified deep learning framework make the proposed architecture a good candidate for reconfigurable platforms.




lear

Biologic and Prognostic Feature Scores from Whole-Slide Histology Images Using Deep Learning. (arXiv:1910.09100v4 [q-bio.QM] UPDATED)

Histopathology is a reflection of the molecular changes and provides prognostic phenotypes representing the disease progression. In this study, we introduced feature scores generated from hematoxylin and eosin histology images based on deep learning (DL) models developed for prostate pathology. We demonstrated that these feature scores were significantly prognostic for time to event endpoints (biochemical recurrence and cancer-specific survival) and had simultaneously molecular biologic associations to relevant genomic alterations and molecular subtypes using already trained DL models that were not previously exposed to the datasets of the current study. Further, we discussed the potential of such feature scores to improve the current tumor grading system and the challenges that are associated with tumor heterogeneity and the development of prognostic models from histology images. Our findings uncover the potential of feature scores from histology images as digital biomarkers in precision medicine and as an expanding utility for digital pathology.




lear

Imitation Learning for Human-robot Cooperation Using Bilateral Control. (arXiv:1909.13018v2 [cs.RO] UPDATED)

Robots are required to operate autonomously in response to changing situations. Previously, imitation learning using 4ch-bilateral control was demonstrated to be suitable for imitation of object manipulation. However, cooperative work between humans and robots has not yet been verified in these studies. In this study, the task was expanded by cooperative work between a human and a robot. 4ch-bilateral control was used to collect training data for training robot motion. We focused on serving salad as a task in the home. The task was executed with a spoon and a fork fixed to robots. Adjustment of force was indispensable in manipulating indefinitely shaped objects such as salad. Results confirmed the effectiveness of the proposed method as demonstrated by the success of the task.




lear

Dynamic Face Video Segmentation via Reinforcement Learning. (arXiv:1907.01296v3 [cs.CV] UPDATED)

For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key scheduling policy, while others proposed adaptive key scheduling methods based on heuristic strategies, both of which may lead to suboptimal global performance. To overcome this limitation, we model the online key decision process in dynamic video segmentation as a deep reinforcement learning problem and learn an efficient and effective scheduling policy from expert information about decision history and from the process of maximising global return. Moreover, we study the application of dynamic video segmentation on face videos, a field that has not been investigated before. By evaluating on the 300VW dataset, we show that the performance of our reinforcement key scheduler outperforms that of various baselines in terms of both effective key selections and running speed. Further results on the Cityscapes dataset demonstrate that our proposed method can also generalise to other scenarios. To the best of our knowledge, this is the first work to use reinforcement learning for online key-frame decision in dynamic video segmentation, and also the first work on its application on face videos.




lear

Ranked List Loss for Deep Metric Learning. (arXiv:1903.03238v6 [cs.CV] UPDATED)

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, ranking-motivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we unveil two limitations of existing ranking-motivated structured losses and propose a novel ranked list loss to solve both of them. First, given a query, only a fraction of data points is incorporated to build the similarity structure. To address this, we propose to build a set-based similarity structure by exploiting all instances in the gallery. The learning setting can be interpreted as few-shot retrieval: given a mini-batch, every example is iteratively used as a query, and the rest ones compose the galley to search, i.e., the support set in few-shot setting. The rest examples are split into a positive set and a negative set. For every mini-batch, the learning objective of ranked list loss is to make the query closer to the positive set than to the negative set by a margin. Second, previous methods aim to pull positive pairs as close as possible in the embedding space. As a result, the intraclass data distribution tends to be extremely compressed. In contrast, we propose to learn a hypersphere for each class in order to preserve useful similarity structure inside it, which functions as regularisation. Extensive experiments demonstrate the superiority of our proposal by comparing with the state-of-the-art methods on the fine-grained image retrieval task.




lear

Machine learning topological phases in real space. (arXiv:1901.01963v4 [cond-mat.mes-hall] UPDATED)

We develop a supervised machine learning algorithm that is able to learn topological phases for finite condensed matter systems from bulk data in real lattice space. The algorithm employs diagonalization in real space together with any supervised learning algorithm to learn topological phases through an eigenvector ensembling procedure. We combine our algorithm with decision trees and random forests to successfully recover topological phase diagrams of Su-Schrieffer-Heeger (SSH) models from bulk lattice data in real space and show how the Shannon information entropy of ensembles of lattice eigenvectors can be used to retrieve a signal detailing how topological information is distributed in the bulk. The discovery of Shannon information entropy signals associated with topological phase transitions from the analysis of data from several thousand SSH systems illustrates how model explainability in machine learning can advance the research of exotic quantum materials with properties that may power future technological applications such as qubit engineering for quantum computing.