India faces a drastic shortage of radiologists with just one radiologist available for 100,000 people living in the country. In comparison, this ratio is one to 10,000 in the US. With such a shortage of qualified professionals in the field, radiologists tend to see hundreds of X-rays in a day making the process error-prone. DeepTek, a Pune-based health-tech firm, has created an AI-based platform, Augmento, that assists radiologists to make faster and accurate diagnoses through X-rays for 20 different pathologies. To understand how the platform works and the advantage it provides in terms of making accurate diagnoses using AI in radiology, Analytics India Magazine caught up with Viraj Kulkarni, Principal Data Scientist at DeepTek.

Artificial intelligence (AI) solutions are facing increased scrutiny due to their aptitude for amplifying both good and bad decisions. More specifically, for their propensity to expose and heighten existing societal biases and inequalities. It is only right, then, that discussions of ethics are taking center stage as AI adoption increases. In lockstep with ethics comes the topic of trust. Ethics are the guiding rules for the decisions we make and actions we take.

Automated reasoning is the general process that gives machine learning algorithms an organized framework to define, approach and solve problems. While more a theoretical field of research than a specific technique itself, automated reasoning underpins many machine learning practices, such as logic programming, fuzzy logic, Bayesian inference, and maximal entropy reasoning. The ultimate goal is to create deep learning systems that can mimic human deduction without human interference.

Good quotes help make us stronger. What is truly inspiring about quotes is not their tone or contentedness but how those who share them reflect life experiences that really serve others. I didn't write the above quote about quotes (Quote-ception; bad pun?), but an AI model I trained did. And it says it better than I would have. Quotes are something that means different things to different people.

But then there was the Chinese game of go (pictured), estimated to be 4000 years old, which offers more "degrees of freedom" (possible moves, strategy, and rules) than chess (2 10170). As futurist George Gilder tells us, in Gaming AI, it was a rite of passage for aspiring intellects in Asia: "Go began as a rigorous rite of passage for Chinese gentlemen and diplomats, testing their intellectual skills and strategic prowess. Later, crossing the Sea of Japan, Go enthralled the Shogunate, which brought it into the Japanese Imperial Court and made it a national cult." Then AlphaGo, from Google's DeepMind, appeared on the scene in 2016: As the Chinese American titan Kai-Fu Lee explains in his bestseller AI Super-powers,8 the riveting encounter between man and machine across the Go board had a powerful effect on Asian youth. Though mostly unnoticed in the United States, AlphaGo's 2016 defeat of Lee Sedol was avidly watched by 280 million Chinese, and Sedol's loss was a shattering experience. The Chinese saw DeepMind as an alien system defeating an Asian man in the epitome of an Asian game.

Chemical kinetics consists of the phenomenological framework for the disentanglement of reaction mechanisms, optimization of reaction performance and the rational design of chemical processes. Here, we utilize feed-forward artificial neural networks as basis functions for the construction of surrogate models to solve ordinary differential equations (ODEs) that describe microkinetic models (MKMs). We present an algebraic framework for the mathematical description and classification of reaction networks, types of elementary reaction, and chemical species. Under this framework, we demonstrate that the simultaneous training of neural nets and kinetic model parameters in a regularized multiobjective optimization setting leads to the solution of the inverse problem through the estimation of kinetic parameters from synthetic experimental data. We probe the limits at which kinetic parameters can be retrieved as a function of knowledge about the chemical system states over time, and assess the robustness of the methodology with respect to statistical noise. This surrogate approach to inverse kinetic ODEs can assist in the elucidation of reaction mechanisms based on transient data.

Uncertainty is ubiquitous with flow in subsurface rocks because of their inherent heterogeneity and lack of in-situ measurements. To complete uncertainty analysis in a multi-scale manner, it is a prerequisite to provide sufficient rock samples. Even though the advent of digital rock technology offers opportunities to reproduce rocks, it still cannot be utilized to provide massive samples due to its high cost, thus leading to the development of diversified mathematical methods. Among them, two-point statistics (TPS) and multi-point statistics (MPS) are commonly utilized, which feature incorporating low-order and high-order statistical information, respectively. Recently, generative adversarial networks (GANs) are becoming increasingly popular since they can reproduce training images with excellent visual and consequent geologic realism. However, standard GANs can only incorporate information from data, while leaving no interface for user-defined properties, and thus may limit the diversity of reconstructed samples. In this study, we propose conditional GANs for digital rock reconstruction, aiming to reproduce samples not only similar to the real training data, but also satisfying user-specified properties. In fact, the proposed framework can realize the targets of MPS and TPS simultaneously by incorporating high-order information directly from rock images with the GANs scheme, while preserving low-order counterparts through conditioning. We conduct three reconstruction experiments, and the results demonstrate that rock type, rock porosity, and correlation length can be successfully conditioned to affect the reconstructed rock images. Furthermore, in contrast to existing GANs, the proposed conditioning enables learning of multiple rock types simultaneously, and thus invisibly saves the computational cost.

Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MARL) has shown phenomenal breakthroughs recently. Strong AIs are achieved for several benchmarks, including Dota 2, Glory of Kings, Quake III, StarCraft II, to name a few. Despite the success, the MARL training is extremely data thirsty, requiring typically billions of (if not trillions of) frames be seen from the environment during training in order for learning a high performance agent. This poses non-trivial difficulties for researchers or engineers and prevents the application of MARL to a broader range of real-world problems. To address this issue, in this manuscript we describe a framework, referred to as TLeague, that aims at large-scale training and implements several main-stream CSP-MARL algorithms. The training can be deployed in either a single machine or a cluster of hybrid machines (CPUs and GPUs), where the standard Kubernetes is supported in a cloud native manner. TLeague achieves a high throughput and a reasonable scale-up when performing distributed training. Thanks to the modular design, it is also easy to extend for solving other multi-agent problems or implementing and verifying MARL algorithms. We present experiments over StarCraft II, ViZDoom and Pommerman to show the efficiency and effectiveness of TLeague. The code is open-sourced and available at https://github.com/tencent-ailab/tleague_projpage

Significance: We demonstrated the potential of using domain adaptation on functional Near-Infrared Spectroscopy (fNIRS) data to classify different levels of n-back tasks that involve working memory. Aim: Domain shift in fNIRS data is a challenge in the workload level alignment across different experiment sessions and subjects. In order to address this problem, two domain adaptation approaches -- Gromov-Wasserstein (G-W) and Fused Gromov-Wasserstein (FG-W) were used. Approach: Specifically, we used labeled data from one session or one subject to classify trials in another session (within the same subject) or another subject. We applied G-W for session-by-session alignment and FG-W for subject-by-subject alignment to fNIRS data acquired during different n-back task levels. We compared these approaches with three supervised methods: multi-class Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). Results: In a sample of six subjects, G-W resulted in an alignment accuracy of 68 $\pm$ 4 % (weighted mean $\pm$ standard error) for session-by-session alignment, FG-W resulted in an alignment accuracy of 55 $\pm$ 2 % for subject-by-subject alignment. In each of these cases, 25 % accuracy represents chance. Alignment accuracy results from both G-W and FG-W are significantly greater than those from SVM, CNN and RNN. We also showed that removal of motion artifacts from the fNIRS data plays an important role in improving alignment performance. Conclusions: Domain adaptation has potential for session-by-session and subject-by-subject alignment of mental workload by using fNIRS data.

This paper investigates the problem of assigning shipping requests to ad hoc couriers in the context of crowdsourced urban delivery. The shipping requests are spatially distributed each with a limited time window between the earliest time for pickup and latest time for delivery. The ad hoc couriers, termed crowdsourcees, also have limited time availability and carrying capacity. We propose a new deep reinforcement learning (DRL)-based approach to tackling this assignment problem. A deep Q network (DQN) algorithm is trained which entails two salient features of experience replay and target network that enhance the efficiency, convergence, and stability of DRL training. More importantly, this paper makes three methodological contributions: 1) presenting a comprehensive and novel characterization of crowdshipping system states that encompasses spatial-temporal and capacity information of crowdsourcees and requests; 2) embedding heuristics that leverage the information offered by the state representation and are based on intuitive reasoning to guide specific actions to take, to preserve tractability and enhance efficiency of training; and 3) integrating rule-interposing to prevent repeated visiting of the same routes and node sequences during routing improvement, thereby further enhancing the training efficiency by accelerating learning. The effectiveness of the proposed approach is demonstrated through extensive numerical analysis. The results show the benefits brought by the heuristics-guided action choice and rule-interposing in DRL training, and the superiority of the proposed approach over existing heuristics in both solution quality, time, and scalability. Besides the potential to improve the efficiency of crowdshipping operation planning, the proposed approach also provides a new avenue and generic framework for other problems in the vehicle routing context.