Of course we discussed how PR is evolving and Martin had some interesting insight into how PR people need to bring visuals into their pitches and try to get a little bit more savvy with photos, video and design. We then spent a lot of time talking about the fascinating intersection between PR and AI (artificial intelligence). Not to toot my own horn, but this was really one of the first times an interviewee brought a topic to the table that I honestly hadn't thought of before. Martin is currently completing a Master in Communications Management from McMaster/Syracuse and researching AI, relationships and communications. His thesis was on the relationships humans have (or will have) with machines, which he calls the human/AI agent relationship.

Machine learning experts at have made a system which can make animations and small videos of motion by using just one photo or painting. The paper of this model was published in Samsung AI Center which can be read on Arvix. According to the study, researchers used artificial neural network techniques to bring facial expressions and body movement in the source imagery. The AI will show the target face talking and make it do what source face does. This technique and system is not entirely new.

Creating eyes is not the same as creating vision. Hand in hand with the general thrust to push more Artificial Intelligence (AI) into our lives is the drive to give computers the ability to'see' what's happening in the world around them. It's important to realize that, for the foreseeable future, those inverted commas around the word'see' will always be there. We can give computers enough intelligence to start categorizing objects scanned in the world around them, but until we start developing semi-organic human-machine cyborgs, technology's ability to'see' will only ever be an abstracted extension of the core processor in the computer itself. "Just like to hear is not the same as to listen, to take pictures is not the same as to see," wrote computer scientist and director of Stanford Vision Lab Fei-Fei Lim in reaction to the current developments in this space at the intersection point between human sight and the growing field of computer vision.

Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many supervised approaches suffer from the problem of scarce human labeled data, whereas abundant unlabeled resources are highly underutilized. To alleviate this problem, an effective solution is to use pre-trained representations for question understanding. However, existing pre-training methods in NLP area are infeasible to learn test question representations due to several domain-specific characteristics in education. First, questions usually comprise of heterogeneous data including content text, images and side information. Second, there exists both basic linguistic information as well as domain logic and knowledge. To this end, in this paper, we propose a novel pre-training method, namely QuesNet, for comprehensively learning question representations. Specifically, we first design a unified framework to aggregate question information with its heterogeneous inputs into a comprehensive vector. Then we propose a two-level hierarchical pre-training algorithm to learn better understanding of test questions in an unsupervised way. Here, a novel holed language model objective is developed to extract low-level linguistic features, and a domain-oriented objective is proposed to learn high-level logic and knowledge. Moreover, we show that QuesNet has good capability of being fine-tuned in many question-based tasks. We conduct extensive experiments on large-scale real-world question data, where the experimental results clearly demonstrate the effectiveness of QuesNet for question understanding as well as its superior applicability.

Prevalent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen. In this paper, we use causal models to derive causal explanations of behaviour of reinforcement learning agents. We present an approach that learns a structural causal model during reinforcement learning and encodes causal relationships between variables of interest. This model is then used to generate explanations of behaviour based on counterfactual analysis of the causal model. We report on a study with 120 participants who observe agents playing a real-time strategy game (Starcraft II) and then receive explanations of the agents' behaviour. We investigated: 1) participants' understanding gained by explanations through task prediction; 2) explanation satisfaction and 3) trust. Our results show that causal model explanations perform better on these measures compared to two other baseline explanation models.

Transcribing content from structural images, e.g., writing notes from music scores, is a challenging task as not only the content objects should be recognized, but the internal structure should also be preserved. Existing image recognition methods mainly work on images with simple content (e.g., text lines with characters), but are not capable to identify ones with more complex content (e.g., structured symbols), which often follow a fine-grained grammar. To this end, in this paper, we propose a hierarchical Spotlight Transcribing Network (STN) framework followed by a two-stage "where-to-what" solution. Specifically, we first decide "where-to-look" through a novel spotlight mechanism to focus on different areas of the original image following its structure. Then, we decide "what-to-write" by developing a GRU based network with the spotlight areas for transcribing the content accordingly. Moreover, we propose two implementations on the basis of STN, i.e., STNM and STNR, where the spotlight movement follows the Markov property and Recurrent modeling, respectively. We also design a reinforcement method to refine the framework by self-improving the spotlight mechanism. We conduct extensive experiments on many structural image datasets, where the results clearly demonstrate the effectiveness of STN framework.

Trick-taking card games feature a large amount of private information that slowly gets revealed through a long sequence of actions. This makes the number of histories exponentially large in the action sequence length, as well as creating extremely large information sets. As a result, these games become too large to solve. To deal with these issues many algorithms employ inference, the estimation of the probability of states within an information set. In this paper, we demonstrate a Policy Based Inference (PI) algorithm that uses player modelling to infer the probability we are in a given state. We perform experiments in the German trick-taking card game Skat, in which we show that this method vastly improves the inference as compared to previous work, and increases the performance of the state-of-the-art Skat AI system Kermit when it is employed into its determinized search algorithm.

Decision-making in large imperfect information games is difficult. Thanks to recent success in Poker, Counterfactual Regret Minimization (CFR) methods have been at the forefront of research in these games. However, most of the success in large games comes with the use of a forward model and powerful state abstractions. In trick-taking card games like Bridge or Skat, large information sets and an inability to advance the simulation without fully determinizing the state make forward search problematic. Furthermore, state abstractions can be especially difficult to construct because the precise holdings of each player directly impact move values. In this paper we explore learning model-free policies for Skat from human game data using deep neural networks (DNN). We produce a new state-of-the-art system for bidding and game declaration by introducing methods to a) directly vary the aggressiveness of the bidder and b) declare games based on expected value while mitigating issues with rarely observed state-action pairs. Although cardplay policies learned through imitation are slightly weaker than the current best search-based method, they run orders of magnitude faster. We also explore how these policies could be learned directly from experience in a reinforcement learning setting and discuss the value of incorporating human data for this task.

Given a large number of covariates $Z$, we consider the estimation of a high-dimensional parameter $\theta$ in an individualized linear threshold $\theta^T Z$ for a continuous variable $X$, which minimizes the disagreement between $\text{sign}(X-\theta^TZ)$ and a binary response $Y$. While the problem can be formulated into the M-estimation framework, minimizing the corresponding empirical risk function is computationally intractable due to discontinuity of the sign function. Moreover, estimating $\theta$ even in the fixed-dimensional setting is known as a nonregular problem leading to nonstandard asymptotic theory. To tackle the computational and theoretical challenges in the estimation of the high-dimensional parameter $\theta$, we propose an empirical risk minimization approach based on a regularized smoothed loss function. The statistical and computational trade-off of the algorithm is investigated. Statistically, we show that the finite sample error bound for estimating $\theta$ in $\ell_2$ norm is $(s\log d/n)^{\beta/(2\beta+1)}$, where $d$ is the dimension of $\theta$, $s$ is the sparsity level, $n$ is the sample size and $\beta$ is the smoothness of the conditional density of $X$ given the response $Y$ and the covariates $Z$. The convergence rate is nonstandard and slower than that in the classical Lasso problems. Furthermore, we prove that the resulting estimator is minimax rate optimal up to a logarithmic factor. The Lepski's method is developed to achieve the adaption to the unknown sparsity $s$ and smoothness $\beta$. Computationally, an efficient path-following algorithm is proposed to compute the solution path. We show that this algorithm achieves geometric rate of convergence for computing the whole path. Finally, we evaluate the finite sample performance of the proposed estimator in simulation studies and a real data analysis.

Ensemble Decision Systems offer a unique form of decision making that allows a collection of algorithms to reason together about a problem. Each individual algorithm has its own inherent strengths and weaknesses, and often it is difficult to overcome the weaknesses while retaining the strengths. Instead of altering the properties of the algorithm, the Ensemble Decision System augments the performance with other algorithms that have complementing strengths. This work outlines different options for building an Ensemble Decision System as well as providing analysis on its performance compared to the individual components of the system with interesting results, showing an increase in the generality of the algorithms without significantly impeding performance.