We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric characterizes whether the output of a DNN on an input can be trusted. DNNs are known to be brittle on inputs outside the training distribution and are, hence, susceptible to adversarial attacks. This fragility is compounded by a lack of effectively computable measures of model confidence that correlate well with the accuracy of DNNs. These factors have impeded the adoption of DNNs in high-assurance systems.

We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric characterizes whether the output of a DNN on an input can be trusted. DNNs are known to be brittle on inputs outside the training distribution and are, hence, susceptible to adversarial attacks. This fragility is compounded by a lack of effectively computable measures of model confidence that correlate well with the accuracy of DNNs. These factors have impeded the adoption of DNNs in high-assurance systems.

We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric characterizes whether the output of a DNN on an input can be trusted. DNNs are known to be brittle on inputs outside the training distribution and are, hence, susceptible to adversarial attacks. This fragility is compounded by a lack of effectively computable measures of model confidence that correlate well with the accuracy of DNNs. These factors have impeded the adoption of DNNs in high-assurance systems.

In this work, we present a method to generate a configurational level fingerprint for polymers using the Bead-Spring-Model. Unlike some of the previous fingerprinting approaches that employ monomer-level information where atomistic descriptors are computed using quantum chemistry calculations, this approach incorporates configurational information from a coarse-grained model of a long polymer chain. The proposed approach may be advantageous for the study of behavior resulting from large molecular weights. To create this fingerprint, we make use of two kinds of descriptors. First, we calculate certain geometric descriptors like Re2, Rg2 etc. and label them as Calculated Descriptors. Second, we generate a set of data-driven descriptors using an unsupervised autoencoder model and call them Learnt Descriptors. Using a combination of both of them, we are able to learn mappings from the structure to various properties of the polymer chain by training ML models. We test our fingerprint to predict the probability of occurrence of a configuration at equilibrium, which is approximated by a simple linear relationship between the instantaneous internal energy and equilibrium average internal energy.

Ashish Ranjan Jha received his Bachelors degree in Electrical Engineering from IIT Roorkee (India), Masters degree in Computer Science from EPFL (Switzerland) and an MBA degree from Quantic School of Business (Washington). He has received distinction in all 3 of his degrees. He has worked for large technology companies like Oracle, Sony as well as the more recent tech unicorns such as Revolut, mostly focussed around Artificial Intelligence. He currently works as a Machine Learning Engineer. Ashish has several years of working experience and specialisation in the field of Machine Learning, and Python is his go-to tool.

Sudhir Jha, senior vice president and head of Mastercard's Brighterion unit, told Karen Webster in the most recent On the Agenda discussion that artificial intelligence (AI) can strengthen credit and risk management and broaden its value well beyond simply improving day-to-day operations. But to get there, enterprises need a bit of guidance. "What used to be cutting-edge technology five years ago is no longer cutting edge," he said, and enterprises that try to keep up with the rapid changes in data science and analysis on their own can be quickly overwhelmed. The enterprise that starts with regression and pattern analysis solutions might scale rapidly and find benefit from neural networks. For banks, acquirers and healthcare payments executives, he said, using vendors' AI-based solutions help to avoid undue losses from fraud, the abuse and misallocation of funds and poor underwriting decisions.

It's been a while since cash was king here in the U.S., but in other parts of the world, such as South America, paper money has managed to retain its grip, albeit slightly diminished as a result of the pandemic's many lifestyle changes that exposed cash transactions as cumbersome and risky. It's a reality that Brighterion's Sudhir Jha told PYMNTS has resulted in a pan-regional progression that is moving more Latin American consumers into digital payment solutions, even though credit penetrations remain low. "There's not a lot of historical data about consumers who are new to digital ecosystem -- that's why there is a desire to go directly to an AI-based solution in many cases, because you want a solution that works today, but also scales really well and attracts more and more customers to your system," Jha explained. That growing regional need for artificial intelligence (AI)-based solutions is what motivated Brazilian insurer Porto Seguro to team with Brighterion. Announced recently, the engagement leveraged Porto Seguro's analytical expertise in combination with Brighterion's AI technology to build high-performance models custom-created to identify risks better.

Led by Sumit Jha, professor in the Department of Computer Science at UTSA, the team has changed the conventional approach employed in explaining machine learning decisions that relies on a single injection of noise into the input layer of a neural network. The team shows that adding noise -- also known as pixilation -- along multiple layers of a network provides a more robust representation of an image that's recognized by the AI and creates more robust explanations for AI decisions. This work aids in the development of what's been called "explainable AI" which seeks to enable high-assurance applications of AI such as medical imaging and autonomous driving. "It's about injecting noise into every layer," Jha said. "The network is now forced to learn a more robust representation of the input in all of its internal layers. If every layer experiences more perturbations in every training, then the image representation will be more robust and you won't see the AI fail just because you change a few pixels of the input image."

Because COVID-19 made it difficult for consumers to venture out and run their usual errands, FIs needed to find other ways to provide their services. The only way for them to really keep up with the speedy digitization was through the implementation of AI systems. To further discuss all things AI, PaymentsJournal sat down with Sudhir Jha, Mastercard SVP and head of Brighterion, and Tim Sloane, VP of Payments Innovation at Mercator Advisory Group. Jha believes that there were two fundamentally big changes that occurred in banking during the pandemic: the environment began constantly shifting, and person-to-person interactions were abruptly limited. "Every week, every month, there were different ways that we were trying to react to the pandemic," explained Jha.

A Bengaluru-based Artificial Intelligence (AI) firm has come up with "designs" of several chemical molecules that may help stop SARS-CoV2 virus, which causes Covid-19 infection from multiplying in an infected person. The firm, which used deep learning technology to identify structures of molecules that would inhibit a critical enzyme of the virus – called 3CLpro, is already in talks with an Indian pharma company, which could synthesise the molecules for testing, if the deal materialises. "We are not in a position to disclose the name of the pharma firm yet," said Vikram Jha, CEO of Pucho Technology Information Limited, the five-year-old firm. The firm, which has office in Bengaluru has been involved in developing an AI platform that offers search and information services to people who have otherwise access to the Internet in languages they are comfortable with when the lockdown happened. "We were ready with our platform but could not launch because of the lockdown. So, we decided to direct our energies towards the Covid-19 fight in a meaningful way using our expertise in AI. That was when two of our engineers specialising in deep learning suggested they could use neural network technology to look for generating potential lead compounds that can target the viral enzyme, 3CLpro," said Jha.