Tumor segmentation in oncological PET images is challenging, a major reason being the partial-volume effects that arise from low system resolution and a finite pixel size. The latter results in pixels containing more than one region, also referred to as tissue-fraction effects. Conventional classification-based segmentation approaches are inherently limited in accounting for the tissue-fraction effects. To address this limitation, we pose the segmentation task as an estimation problem. We propose a Bayesian method that estimates the posterior mean of the tumorfraction area within each pixel and uses these estimates to define the segmented tumor boundary. The method was implemented using an autoencoder. Quantitative evaluation of the method was performed using realistic simulation studies conducted in the context of segmenting the primary tumor in PET images of patients with lung cancer. For these studies, a framework was developed to generate clinically realistic simulated PET images. Realism of these images was quantitatively confirmed using a two-alternative-forced-choice study by six trained readers with expertise in reading PET scans. The evaluation studies demonstrated that the proposed segmentation method was accurate, significantly outperformed widely used conventional methods on the tasks of tumor segmentation and estimation of tumor-fraction areas, was relatively insensitive to partial-volume effects, and reliably estimated the ground-truth tumor boundaries. Further, these results were obtained across different clinical-scanner configurations. This proof-of-concept study demonstrates the efficacy of an estimation-based approach to PET segmentation.

Corvids, apes, and children solve The Crow and The Pitcher task (from Aesop's Fables) indicating a causal understanding of the task. By cumulatively interacting with different objects, how can cognitive agents abstract the underlying cause-effect relations to predict affordances of novel objects? We address this question by re-enacting the Aesop's Fable task on a robot and present a) a brain-guided neural model of semantic-episodic memory; with b) four task-agnostic learning rules that compare expectations from recalled past episodes with the current scenario to progressively extract the hidden causal relations. The ensuing robot behaviours illustrate causal learning; and predictions for novel objects converge to Archimedes' principle, independent of both the objects explored during learning and the order of their cumulative exploration.

In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of artificial intelligence, in particular machine learning, are statistical models. Safety assessment would then have t o concentrate on the model that is used in AI, besides the normal assessment procedure. Part of the budget of dangerous random failures for the relevant safety integrity level needs to be used for the probabilistic faulty behavior of the AI system. We demonstrate our thoughts with a simple example and propose a research challenge that may be decisive for the use of AI in safety related systems.

Morphological analyzers are the essential milestones for many linguistic applications like; machine translation, word sense disambiguation, spells checkers, and search engines etc. Therefore, development of an effective morphological analyzer has a greater impact on the computational recognition of a language. In this paper, we present a finite state transducer based inflectional morphological analyzer for a resource poor language of India, known as Maithili. Maithili is an eastern Indo-Aryan language spoken in the eastern and northern regions of Bihar in India and the southeastern plains, known as tarai of Nepal. This work can be recognized as the first work towards the computational development of Maithili which may attract researchers around the country to up-rise the language to establish in computational world.

When people buy products online, they primarily base their decisions on the recommendations of others given in online reviews. The current work analyzed these online reviews by sentiment analysis and used the extracted sentiments as features to predict the product ratings by several machine learning algorithms. These predictions were disentangled by various meth-ods of explainable AI (XAI) to understand whether the model showed any bias during prediction. Study 1 benchmarked these algorithms (knn, support vector machines, random forests, gradient boosting machines, XGBoost) and identified random forests and XGBoost as best algorithms for predicting the product ratings. In Study 2, the analysis of global feature importance identified the sentiment joy and the emotional valence negative as most predictive features. Two XAI visualization methods, local feature attributions and partial dependency plots, revealed several incorrect prediction mechanisms on the instance-level. Performing the benchmarking as classification, Study 3 identified a high no-information rate of 64.4% that indicated high class imbalance as underlying reason for the identified problems. In conclusion, good performance by machine learning algorithms must be taken with caution because the dataset, as encountered in this work, could be biased towards certain predictions. This work demonstrates how XAI methods reveal such prediction bias.

Image animation consists of generating a video sequence so that an object in a source image is animated according to the motion of a driving video. Our framework addresses this problem without using any annotation or prior information about the specific object to animate. Once trained on a set of videos depicting objects of the same category (\eg \ faces, human bodies), our method can be applied to any object of this class. To achieve this, we decouple appearance and motion information using a self-supervised formulation. To support complex motions, we use a representation consisting of a set of learned keypoints along with their local affine transformations. A generator network models occlusions arising during target motions and combines the appearance extracted from the source image and the motion derived from the driving video. Our framework scores best on diverse benchmarks and on a variety of object categories. Our source code is publicly available.

Exploration in sparse reward environments remains one of the key challenges of model-free reinforcement learning. Instead of solely relying on extrinsic rewards provided by the environment, many state-of-the-art methods use intrinsic rewards to encourage exploration. However, we show that existing methods fall short in procedurally-generated environments where an agent is unlikely to visit a state more than once. We propose a novel type of intrinsic reward which encourages the agent to take actions that lead to significant changes in its learned state representation. We evaluate our method on multiple challenging procedurally-generated tasks in MiniGrid, as well as on tasks with high-dimensional observations used in prior work. Our experiments demonstrate that this approach is more sample efficient than existing exploration methods, particularly for procedurally-generated MiniGrid environments. Furthermore, we analyze the learned behavior as well as the intrinsic reward received by our agent. In contrast to previous approaches, our intrinsic reward does not diminish during the course of training and it rewards the agent substantially more for interacting with objects that it can control.

The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is always possible to approximate the input-output relations of deep neural networks with human-understandable rules or a post-hoc model, the discovery of the double descent phenomena suggests that no such approximation will ever map onto the actual mechanistic functioning of deep neural networks. Double descent indicates that deep neural networks typically operate by smoothly interpolating between data points rather than by extracting a few high level rules. As a result neural networks trained on complex real world data are inherently hard to interpret and prone to failure if used outside their domain of applicability (ie, for extrapolation). To show how we might be able to trust AI despite these problems, we introduce the concept of self-explaining AI. Self-explaining AIs are capable of providing a human-understandable explanation of each decision along with confidence levels for both the decision and explanation. Some difficulties to this approach along with possible solutions are sketched. Finally, we argue it is also important that AI systems warn their user when they are asked to perform outside their domain of applicability.

Ethical concerns around potential job loss, facial recognition, and bias have been raised surrounding the future impact of artificial intelligence on society. On Friday those concerns were elevated to a "higher authority," with IBM and Microsoft lending support to a set of ethical principles backed by the Vatican. Such principles were outlined in a document titled "Rome Call For AI Ethics," and promotes a regulatory approach around what is being called an "algor-ethical" vision of design, with transparency, inclusion, responsibility, impartiality, reliability, security and privacy all factored in. "AI systems must be conceived, designed and implemented to serve and protect human beings and the environment in which they live," the document reads. "It must include every human being, discriminating against no one; it must have the good of humankind and the good of every human being at its heart; finally, it must be mindful of the complex reality of our ecosystem and be characterized by the way in which it cares for and protects the planet…."

Artificial intelligence (AI) can be used to identify outbreaks such as the coronavirus, which, to date, has resulted in nearly 1,800 reported deaths and more than reported 71,000 infections. In a February 13 webinar, Casey Ross, national technology correspondent for STAT, pointed to efforts by John Brownstein, PhD, chief innovation officer at Boston Children's Hospital, to use machine learning to review social media posts, reports by physicians, news outlets, and information released by official public health entities to assess the condition's outbreak beyond China's borders. Brownstein's work is proof that AI is showing its value in tracking the outbreak of the disease, says Ross. Closer to home, healthcare systems around the country use AI to inform operational tasks such as scheduling. Some healthcare organizations use AI to pinpoint patients who need additional care, says Ross. For example, it's used in sepsis detection and prediction, the assessment of readmission risk, and the identification of patients who are deteriorating.