The Institute for the Future (IFTF) in Palo Alto, CA, is a U.S.-based think tank. It was established in 1968 as a spin-off from the RAND Corporation to help organizations plan for the long-term future. Roy Amara, who passed away in 2007, was IFTF's president from 1971 until 1990. Amara is best known for coining Amara's Law on the effect of technology: "We tend to overestimate the effect of a technology in the short run and underestimate the effect in the long run." This law is best illustrated by the Gartner Hype Cycle,a characterized by the "peak of inflated expectations," followed by the "trough of disillusionment," then the "slope of enlightenment," and, finally, the "plateau of productivity."

In this article, I'm going to tell you about automating corporate strategies using artificial intelligence, and look at some recent progress in automatically generating strategies in the face of uncertainty. Every day, progress in artificial intelligence is addressing tasks currently performed only by humans, and it's worthwhile to take a short-term view of what this all means to your company. Games like chess have been tackled by artificial intelligence with amazing results, but there was this big gap between those games - where everything about the game state and consequences is known before making a decision - and the reality of life where, like poker, there is only a little bit of information available to the decision-makers, and the quality and quantity of information used to make decisions varies wildly. We humans face this situation of high uncertainty every time we cross the street or eat a hamburger, but it doesn't seem to bother us. Until recently, computers have had a lot of trouble dealing with games that give the decision-maker incomplete information about the state of the game.

For more than half a century our digital search engines have relied upon the humble keyword. Yet over the past few years, search engines of all kinds have increasingly turned to deep learning-powered categorization and recommendation algorithms to augment and slowly replace the traditional keyword search. Behavioral and interest-based personalization has further eroded the impact of keyword searches, meaning that if ten people all search for the same thing, they may all get different results. As search engines depreciate traditional raw "search" in favor of AI-assisted navigation, the concept of informational access is being harmed and our digital world is being redefined by the limitations of today's AI. At first glance, the evolution of search from simple TF-IDF keyword queries into today's AI-powered personalized digital navigation is a positive step towards making the digital world more accessible to the general public.

AI should be built on rigorous knowledge... Note: This is a follow-up to an earlier article on causal machine learning, "AI Needs More Why". There's much to be excited about with artificial intelligence (AI) in healthcare: Google AI is improving the workflow of clinicians with predictive models for diabetic retinopathy [2], many new approaches are achieving expert-level performance in tasks such as classification of skin cancer [3], and others surpassing the capabilities of doctors -- notably the recent report of DeepMind's AI for predicting acute kidney disease, capable of detecting potentially fatal kidney injuries 48 hours before symptoms are recognized by doctors [4]. Yet medical practitioners and researchers at the intersection of machine learning (ML) and medicine are quick to point out these successes are not representative of the more nuanced, non-trivial challenges presented by medical research and clinical applications. These ML success stories (notably all deep learning) are disease prediction problems, learning patterns that map well-defined inputs to well-labeled outputs [5]. Domains where instinctive pattern recognition works powerfully are what psychologist Robin Hogarth termed "kind learning environments" [6].

As a subfield of machine learning, \emph{reinforcement learning} (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised learning methods that usually rely on one-shot, exhaustive and supervised reward signals, RL tackles with sequential decision making problems with sampled, evaluative and delayed feedback simultaneously. Such distinctive features make RL technique a suitable candidate for developing powerful solutions in a variety of healthcare domains, where diagnosing decisions or treatment regimes are usually characterized by a prolonged and sequential procedure. This survey will discuss the broad applications of RL techniques in healthcare domains, in order to provide the research community with systematic understanding of theoretical foundations, enabling methods and techniques, existing challenges, and new insights of this emerging paradigm. By first briefly examining theoretical foundations and key techniques in RL research from efficient and representational directions, we then provide an overview of RL applications in a variety of healthcare domains, ranging from dynamic treatment regimes in chronic diseases and critical care, automated medical diagnosis from both unstructured and structured clinical data, as well as many other control or scheduling domains that have infiltrated many aspects of a healthcare system. Finally, we summarize the challenges and open issues in current research, and point out some potential solutions and directions for future research.

We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale variations and the arbitrary perspective of an individual image. The proposed model has two related tasks, with Crowd Density Estimation as the main task and Crowd-Count Group Classification as the auxiliary task. The auxiliary task helps in capturing the relevant scale-related information to improve the performance of the main task. The main task model comprises two blocks: VGG-16 front-end for feature extraction and a dilated Convolutional Neural Network for density map generation. The auxiliary task model shares the same front-end as the main task, followed by a CNN classifier. Our proposed network achieves 5.8% and 14.9% lower Mean Absolute Error (MAE) than the state-of-the-art methods on ShanghaiTech dataset without using any data augmentation. Our model also outperforms with 10.5% lower MAE on UCF_CC_50 dataset.

Online health communities such as the online breast cancer forum enable patients (i.e., users) to interact and help each other within various subforums, which are subsections of the main forum devoted to specific health topics. The changing nature of the users' activities in different subforums can be strong indicators of their health status changes. This additional information could allow health-care organizations to respond promptly and provide additional help for the patient. However, modeling complex transitions of an individual user's activities among different subforums over time and learning how these correspond to his/her health stage are extremely challenging. In this paper, we first formulate the transition of user activities as a dynamic graph with multi-attributed nodes, then formalize the health stage inference task as a dynamic graph-to-sequence learning problem, and hence propose a novel dynamic graph-to-sequence neural networks architecture (DynGraph2Seq) to address all the challenges. Our proposed DynGraph2Seq model consists of a novel dynamic graph encoder and an interpretable sequence decoder that learn the mapping between a sequence of time-evolving user activity graphs and a sequence of target health stages. We go on to propose dynamic graph hierarchical attention mechanisms to facilitate the necessary multi-level interpretability. A comprehensive experimental analysis of its use for a health stage prediction task demonstrates both the effectiveness and the interpretability of the proposed models.

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. As a response to this controversy, we present a set of tests that provide a bridge between, on the one hand, the vast amount of linguistic and philosophical theory about compositionality and, on the other, the successful neural models of language. We collect different interpretations of compositionality and translate them into five theoretically grounded tests that are formulated on a task-independent level. In particular, we provide tests to investigate (i) if models systematically recombine known parts and rules (ii) if models can extend their predictions beyond the length they have seen in the training data (iii) if models' composition operations are local or global (iv) if models' predictions are robust to synonym substitutions and (v) if models favour rules or exceptions during training. To demonstrate the usefulness of this evaluation paradigm, we instantiate these five tests on a highly compositional data set which we dub PCFG SET and apply the resulting tests to three popular sequence-to- sequence models: a recurrent, a convolution based and a transformer model. We provide an in depth analysis of the results, that uncover the strengths and weaknesses of these three architectures and point to potential areas of improvement.

Neural encoding and decoding, which aim to characterize the relationship between stimuli and brain activities, have emerged as an important area in cognitive neuroscience. Traditional encoding models, which focus on feature extraction and mapping, consider the brain as an input-output mapper without inner states. In this work, inspired by the fact that human brain acts like a state machine, we proposed a novel encoding framework that combines information from both the external world and the inner state to predict brain activity. The framework comprises two parts: forward encoding model that deals with visual stimuli and inner state model that captures influence from intrinsic connections in the brain. The forward model can be any traditional encoding model, making the framework flexible. The inner state model is a linear model to utilize information in the prediction residuals of the forward model. The proposed encoding framework can achieve much better performance on natural image identification from fMRI response than forwardonly models. The identification accuracy will decrease slightly with the dataset size increasing, but remain relatively stable with different identification methods. The results confirm that the new encoding framework is effective and robust when used for brain decoding.

Program synthesis using inputs and outputs is a fundamental problem in computer science. Towards that end, we present a framework, called NetSyn, that synthesizes programs using an evolutionary algorithm. NetSyn makes several novel contributions. First, NetSyn uses neural networks as a fitness function. This addresses the principal challenge of evolutionary algorithm: how to design the most effective fitness function. Second, NetSyn combines an evolutionary algorithm with neighborhood search to expedite the convergence process. Third, NetSyn can support a variety of neural network fitness functions uniformly. We evaluated NetSyn to generate programs in a list-based domain specific language. We compared the proposed approach against a state-of-the-art approach to show that NetSyn performs better in synthesizing programs.