Some say that artificial intelligence (AI) will radically change healthcare in the future. But that prediction overlooks an important detail: AI is already significantly changing healthcare. IBM (NYSE:IBM) Watson Health general manager Deborah DiSanzo spoke at the annual J. P. Morgan Healthcare Conference on Wednesday. She provided an update on the progress that IBM Watson, the AI system famous for beating Jeopardy! DiSanzo highlighted four areas where AI is making a big difference today.

In thinking about how artificial intelligence works, it is not difficult to arrive at the analogy of a human brain, learning over time from the information it is provided, seeking patterns in that information to optimize its ability to apply those learnings to similar or never-before-seen problems. However, the power of AI lies in its ability to process infinitely greater volumes of information, including streaming data, to detect patterns that may otherwise never be detectible to the human brain. This kind of superpower can be useful when processing over one hundred billion transactions per year and seeking, in real time, to detect costly fraud. This is how, using artificial intelligence technologies such as smart agents, neural networks, and case-based reasoning, Brighterion has been able to transform how fraud is detected and prevented across payment, healthcare and credit risk lifecycle ecosystems. As AI continues to enable, improve and automate a growing number of tasks and processes across different industries, it is not only shifting how companies conduct business, it is also increasingly curating our daily experiences and shaping how we as individuals interact with our world.

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic. We also identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem. Some of these problems are classically important, and some are recent problems that have arisen in the last few years. These problems are: (1) Optimizing sparse logical models such as decision trees; (2) Optimization of scoring systems; (3) Placing constraints into generalized additive models to encourage sparsity and better interpretability; (4) Modern case-based reasoning, including neural networks and matching for causal inference; (5) Complete supervised disentanglement of neural networks; (6) Complete or even partial unsupervised disentanglement of neural networks; (7) Dimensionality reduction for data visualization; (8) Machine learning models that can incorporate physics and other generative or causal constraints; (9) Characterization of the "Rashomon set" of good models; and (10) Interpretable reinforcement learning. This survey is suitable as a starting point for statisticians and computer scientists interested in working in interpretable machine learning.

Ian Watson, Rosina O Weber, David Leake Case-based reasoning is reasoning from experience, solving new problems and interpreting new situations by retrieving and adapting prior cases. The Twenty-Eight International Conference on Case-Based Reasoning (ICCBR2020) was held from June 8-12, 2020, with program chairs Ian Watson and Rosina Weber. The conference was originally scheduled for Salamanca, Spain, a World Heritage site, under the auspices of local chair Juan Manuel Corchado and the University of Salamanca. Its theme, "CBR Across Bridges", reflected the goal of bringing together researchers and practitioners with relevant work across various AI areas. Before the conference, the pandemic struck, with tragic effects. The conference chairs resolved to continue with a safe alternative: the first virtual ICCBR. With researchers unable to travel, the virtual conference not only bridged AI areas but geographic ones: 141 conference attendees participated from 23 countries.

In general, one vulnerability with chatbot development frameworks is the turn-around time to go from development to testing. Changes are made to the chatbot application, and a lengthy process needs to be followed to save, deploy, restart the testing environment, and start a test conversation. And obviously this is an iterative process. This is especially debilitating when troubleshooting and much time is lost during this process. Another challenge, in general, with testing chatbots is that the test environment and development environments are really separated and not integrated.

Multiple Instance Learning (MIL) gains popularity in many real-life machine learning applications due to its weakly supervised nature. However, the corresponding effort on explaining MIL lags behind, and it is usually limited to presenting instances of a bag that are crucial for a particular prediction. In this paper, we fill this gap by introducing ProtoMIL, a novel self-explainable MIL method inspired by the case-based reasoning process that operates on visual prototypes. Thanks to incorporating prototypical features into objects description, ProtoMIL unprecedentedly joins the model accuracy and fine-grained interpretability, which we present with the experiments on five recognized MIL datasets.

Previous research in interpretable machine learning (IML) and explainable artificial intelligence (XAI) can be broadly categorized as either focusing on seeking interpretability in the agent's model (i.e., IML) or focusing on the context of the user in addition to the model (i.e., XAI). The former can be categorized as feature or instance attribution. Example- or sample-based methods such as those using or inspired by case-based reasoning (CBR) rely on various approaches to select instances that are not necessarily attributing instances responsible for an agent's decision. Furthermore, existing approaches have focused on interpretability and explainability but fall short when it comes to accountability. Inspired in case-based reasoning principles, this paper introduces a pseudo-metric we call Longitudinal distance and its use to attribute instances to a neural network agent's decision that can be potentially used to build accountable CBR agents.

When venturing into the field of chatbots and Conversational AI, usually the process starts with a search of what frameworks are available. Invariably this leads you to one of the big cloud Chatbot service providers. Most probably you will end up using IBM Watson Assistant, Microsoft LUIS/Bot Framework, Google Dialog Flow etc. There are advantages…these environments offer easy entry in terms of cost and a low-code or no-code approach. However, one big impediment you often run into with these environments, is the lack of diversity when it comes to language options. This changed 17 June 2021 when IBM introduced the Universal language model.

Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that none of the standard regularization techniques mitigate such overfitting. We investigate whether the choice of the loss function can affect this memorization. We empirically show, with benchmark data sets MNIST and CIFAR-10, that a symmetric loss function, as opposed to either cross-entropy or squared error loss, results in significant improvement in the ability of the network to resist such overfitting. We then provide a formal definition for robustness to memorization and provide a theoretical explanation as to why the symmetric losses provide this robustness. Our results clearly bring out the role loss functions alone can play in this phenomenon of memorization.

Memorization studies of deep neural networks (DNNs) help to understand what patterns and how do DNNs learn, and motivate improvements to DNN training approaches. In this work, we investigate the memorization properties of SimCLR, a widely used contrastive self-supervised learning approach, and compare them to the memorization of supervised learning and random labels training. We find that both training objects and augmentations may have different complexity in the sense of how SimCLR learns them. Moreover, we show that SimCLR is similar to random labels training in terms of the distribution of training objects complexity.