We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by exploiting stable patterns in loss surfaces. Our method implicitly estimates the gradients of a scaled loss function while retaining the general properties intact for parameter updates. Besides providing improved performance on few-shot tasks, our framework could be easily extended to do network architecture search. We further propose a novel dual encoder, affinity-score based decoder topology that achieves additional improvements to performance. Experiments on an internal dataset, MQ2007, and AwA2 show our approach outperforms existing alternative approaches by 21%, 8%, and 4% respectively on accuracy and NDCG metrics. On Mini-ImageNet dataset our approach achieves comparable results with Prototypical Networks. Empirical evaluations demonstrate that our approach provides a unified and effective framework.

Analyzing fashion trends is essential in the fashion industry. Current fashion forecasting firms, such as WGSN, utilize the visual information from around the world to analyze and predict fashion trends. However, analyzing fashion trends is time-consuming and extremely labor intensive, requiring individual employees' manual editing and classification. To improve the efficiency of data analysis of such image-based information and lower the cost of analyzing fashion images, this study proposes a data-driven quantitative abstracting approach using an artificial intelligence (A.I.) algorithm. Specifically, an A.I. model was trained on fashion images from a large-scale dataset under different scenarios, for example in online stores and street snapshots. This model was used to detect garments and classify clothing attributes such as textures, garment style, and details for runway photos and videos. It was found that the A.I. model can generate rich attribute descriptions of detected regions and accurately bind the garments in the images. Adoption of A.I. algorithm demonstrated promising results and the potential to classify garment types and details automatically, which can make the process of trend forecasting more cost-effective and faster.

Adversarial Imitation Learning (AIL) is a class of algorithms in Reinforcement learning (RL), which tries to imitate an expert without taking any reward from the environment and does not provide expert behavior directly to the policy training. Rather, an agent learns a policy distribution that minimizes the difference from expert behavior in an adversarial setting. Adversarial Inverse Reinforcement Learning (AIRL) leverages the idea of AIL, integrates a reward function approximation along with learning the policy, and shows the utility of IRL in the transfer learning setting. But the reward function approximator that enables transfer learning does not perform well in imitation tasks. We propose an Off-Policy Adversarial Inverse Reinforcement Learning (Off-policy-AIRL) algorithm which is sample efficient as well as gives good imitation performance compared to the state-of-the-art AIL algorithm in the continuous control tasks. For the same reward function approximator, we show the utility of learning our algorithm over AIL by using the learned reward function to retrain the policy over a task under significant variation where expert demonstrations are absent.

In the majority of executive domains, a notion of normality is involved in most strategic decisions. However, few data-driven tools that support strategic decision-making are available. We introduce and extend the use of autoencoders to provide strategically relevant granular feedback. A first experiment indicates that experts are inconsistent in their decision making, highlighting the need for strategic decision support. Furthermore, using two large industry-provided human resources datasets, the proposed solution is evaluated in terms of ranking accuracy, synergy with human experts, and dimension-level feedback. This three-point scheme is validated using (a) synthetic data, (b) the perspective of data quality, (c) blind expert validation, and (d) transparent expert evaluation. Our study confirms several principal weaknesses of human decision-making and stresses the importance of synergy between a model and humans. Moreover, unsupervised learning and in particular the autoencoder are shown to be valuable tools for strategic decision-making.

ESF thus beckons the valuation of ecosystem services (VES) as a means to signalling nature's contribution to the (re)production of value (Barbier et al., 2009; Villa et al., 2009; Fisher et al., 2010; Gómez-Baggethun et al., 2016); for value is the central category of modern capitalist societies, and the valorisation of value -- i.e., economic growth sublimated into economic development -- their driving force (see, e.g., Mankiw (2016) and Holden et al. (2017)). VES is, in this sense, inscribed in an interpretive approach to modern capitalist praxis, not only invoking assumptions that are instrumentally validated in a retroactive manner, but also taking for granted precisely those historical and material conditions which VES is meant to interpret and, in doing so, reproduce. Overlooking the historical basis of ESF and VES has important practical consequences. When VES practitioners elicit value, a moment or specific field of the social praxis embodied in the valorisation of value is inaugurated, allowing value to mediate other social constructs built around the idea of nature. Since the patterns of actions that make up the capitalist social praxis are presupposed within this new ambit, value takes on a transhistorical quality that justifies its allencompassing and unreflective usage (see, e.g., Badura et al. (2016) and Gómez-Baggethun and Martín-López (2015)).

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called `Student-Teacher' (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically for vision tasks. In general, we consider some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning.

David Mindell has spent his career defying traditional distinctions between disciplines. His work has explored the ways humans interact with machines, drive innovation, and maintain societal well-being as technology transforms our economy. And, Mindell says, he couldn't have done it anywhere but MIT. He joined MIT's faculty 23 years ago after completing his PhD in the Program in Science, Technology, and Society, and he currently holds a dual appointment in engineering and humanities as the Frances and David Dibner Professor of the History of Engineering and Manufacturing in the School of Humanities, Arts, and Social Sciences and professor of aeronautics and astronautics. Mindell's experience combining fields of study has shaped his ideas about the relationship between humans and machines.

A three-year effort by hundreds of engineers worldwide resulted in the publication in March of 2019 of Ethically Aligned Design (EAD) for Business, a guide for policymakers, engineers, designers, developers and corporations. The effort was headed by the IEEE Global Initiative on Ethics of Autonomous and Intelligent Systems (A/IS), with John C. Havens as Executive Director, who spoke to AI Trends for an Executive Interview. We recently connected to ask how the effort has been going. EAD First Edition, a 290-page document which Havens refers to as "applied ethics," has seen some uptake, for example by IBM, which referred to the IEEE effort within their own resource called Everyday Ethics for AI The IBM document is 26 pages, easy to digest, structured into five areas of focus, each with recommended action steps and an example. The example for Accountability involved an AI team developing applications for a hotel.

The graph represents a network of 1,103 Twitter users whose recent tweets contained "Thomas Harrer", or who were replied to or mentioned in those tweets, taken from a data set limited to a maximum of 18,000 tweets. The network was obtained from Twitter on Wednesday, 29 April 2020 at 01:43 UTC. The tweets in the network were tweeted over the 7-day, 15-hour, 26-minute period from Tuesday, 21 April 2020 at 10:08 UTC to Wednesday, 29 April 2020 at 01:35 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods. These tweets may expand the complete time period of the data.

Will full AI try to evade being revealed for what it is. AI is not yet akin to human intelligence and the odds are that we are a long way distant from the promise of such vaunted capabilities. Those touting the use of Machine Learning (ML) and Deep Learning (DL) are hoping that the advent of ML/DL might be a path toward full AI, though right now ML/DL is mainly a stew of computationally impressive pattern matching and we don't know if it will scale-up to anything approaching an equivalent of the human brain. The struggle and earnestness toward achieving full AI is nonetheless still a constant drumbeat of those steeped in AI and the belief is that we will eventually craft or invent a machine-based artificial intelligence made entirely out of software and hardware. One question often posed about reaching full AI is whether or not there will be a need to attain sentience.