We introduce a new approach to functional causal modeling from observational data. The approach, called Causal Generative Neural Networks (CGNN), leverages the power of neural networks to learn a generative model of the joint distribution of the observed variables, by minimizing the Maximum Mean Discrepancy between generated and observed data. An approximate learning criterion is proposed to scale the computational cost of the approach to linear complexity in the number of observations. The performance of CGNN is studied throughout three experiments. First, we apply CGNN to the problem of cause-effect inference, where two CGNNs model $P(Y|X,\textrm{noise})$ and $P(X|Y,\textrm{noise})$ identify the best causal hypothesis out of $X\rightarrow Y$ and $Y\rightarrow X$. Second, CGNN is applied to the problem of identifying v-structures and conditional independences. Third, we apply CGNN to problem of multivariate functional causal modeling: given a skeleton describing the dependences in a set of random variables $\{X_1, \ldots, X_d\}$, CGNN orients the edges in the skeleton to uncover the directed acyclic causal graph describing the causal structure of the random variables. On all three tasks, CGNN is extensively assessed on both artificial and real-world data, comparing favorably to the state-of-the-art. Finally, we extend CGNN to handle the case of confounders, where latent variables are involved in the overall causal model.

In this article we show the duality between tensor networks and undirected graphical models with discrete variables. We study tensor networks on hypergraphs, which we call tensor hypernetworks. We show that the tensor hypernetwork on a hypergraph exactly corresponds to the graphical model given by the dual hypergraph. We translate various notions under duality. For example, marginalization in a graphical model is dual to contraction in the tensor network. Algorithms also translate under duality. We show that belief propagation corresponds to a known algorithm for tensor network contraction. This article is a reminder that the research areas of graphical models and tensor networks can benefit from interaction.

We introduce a novel kernel that models input-dependent couplings across multiple latent processes. The pairwise joint kernel measures covariance along inputs and across different latent signals in a mutually-dependent fashion. A latent correlation Gaussian process (LCGP) model combines these non-stationary latent components into multiple outputs by an input-dependent mixing matrix. Probit classification and support for multiple observation sets are derived by Variational Bayesian inference. Results on several datasets indicate that the LCGP model can recover the correlations between latent signals while simultaneously achieving state-of-the-art performance. We highlight the latent covariances with an EEG classification dataset where latent brain processes and their couplings simultaneously emerge from the model.

Humans are remarkably adept at generalizing knowledge between experiences in a way that can be difficult for computers. Often, this entails generalizing constituent pieces of experiences that do not fully overlap, but nonetheless share useful similarities with, previously acquired knowledge. However, it is often unclear how knowledge gained in one context should generalize to another. Previous computational models and data suggest that rather than learning about each individual context, humans build latent abstract structures and learn to link these structures to arbitrary contexts, facilitating generalization. In these models, task structures that are more popular across contexts are more likely to be revisited in new contexts.

Restricted Boltzmann machines (RBMs) are energy-based neural-networks which are commonly used as the building blocks for deep architectures neural architectures. In this work, we derive a deterministic framework for the training, evaluation, and use of RBMs based upon the Thouless-Anderson-Palmer (TAP) mean-field approximation of widely-connected systems with weak interactions coming from spin-glass theory. While the TAP approach has been extensively studied for fully-visible binary spin systems, our construction is generalized to latent-variable models, as well as to arbitrarily distributed real-valued spin systems with bounded support. In our numerical experiments, we demonstrate the effective deterministic training of our proposed models and are able to show interesting features of unsupervised learning which could not be directly observed with sampling. Additionally, we demonstrate how to utilize our TAP-based framework for leveraging trained RBMs as joint priors in denoising problems.

Recent advances in artificial intelligence are encouraging governments and corporations to deploy AI in high-stakes settings including driving cars autonomously, managing the power grid, trading on stock exchanges, and controlling autonomous weapons systems. Such applications require AI methods to be robust to both the known unknowns (those uncertain aspects of the world about which the computer can reason explicitly) and the unknown unknowns (those aspects of the world that are not captured by the system’s models). This article discusses recent progress in AI and then describes eight ideas related to robustness that are being pursued within the AI research community. While these ideas are a start, we need to devote more attention to the challenges of dealing with the known and unknown unknowns. These issues are fascinating, because they touch on the fundamental question of how finite systems can survive and thrive in a complex and dangerous world

Suppose there exist three machine learning experts that would like to understand the fundamental limits of classification (Bayes error) [1] for a specific dataset. Since the true distribution that generates the data is unknown, they take three different approaches: 1) Expert A: given empirical training samples, produce an estimate of the Bayes error that is (near) optimal statistically; 2) Expert B: construct a (near) optimal classifier based on the training sample, and then use its performance on the test set (may have infinite size) to estimate the Bayes error; 3) Expert C: use the training error of a (near) optimal classification algorithm to estimate the Bayes error. We ask the question: are there any fundamental differences between experts A, B, and C? Evidently, expert A is not constrained by any specific approaches as experts B and C are, but if B and C are using (near) optimal classification algorithms, would B or C achieve the same performance of A if A chooses to act optimally? Similar situations arise in the understanding of fundamental limits of data compression and sequential prediction under logarithmic loss, which is given by the Shannon entropy rate [2]. In this situation, there could exist four different experts: 1) A: would like to estimate the limits of compression (near) optimally; 2) B: would like to construct a predictor based on training samples and use its prediction accuracy under logarithmic loss on the test set (may have infinite size) to estimate the limits; 3) C: would like to use the training error of a (near) optimal sequential predictor to estimate the limits; 4) D: would like to construct a (near) optimal data compressor and use its normalized code length to estimate the limits. In this situation, are there any fundamental differences between the tasks of these four experts?

In this paper, we introduce an approach to automated story generation using Markov Chain Monte Carlo (MCMC) sampling. This approach uses a sampling algorithm based on Metropolis-Hastings to generate a probability distribution which can be used to generate stories via random sampling that adhere to criteria learned by recurrent neural networks. We show the applicability of our technique through a case study where we generate novel stories using an acceptance criteria learned from a set of movie plots taken from Wikipedia. This study shows that stories generated using this approach adhere to this criteria 85%-86% of the time.

In this paper we introduce Bardo, a real-time intelligent system to automatically select the background music for tabletop role-playing games. Bardo uses an off-the-shelf speech recognition system to transform into text what the players say during a game session, and a supervised learning algorithm to classify the text into an emotion. Bardo then selects and plays as background music a song representing the classified emotion. We evaluate Bardo with a Dungeons and Dragons (D&D) campaign available on YouTube. Accuracy experiments show that a simple Naive Bayes classifier is able to obtain good prediction accuracy in our classification task. A user study in which people evaluated edited versions of the D&D videos suggests that Bardo's selections can be better than those used in the original videos of the campaign.

Player modeling is an important concept that has gained much attention in game research due to its utility in developing adaptive techniques to target better designs for engagement and retention. Previous work has explored modeling individual differences using machine learning algorithms performed on aggregated game actions. However, players’ individual differences may be better manifested through sequential patterns of the in-game player’s actions. While few works have explored sequential analysis of player data, none have explored the use of Hidden Markov Models (HMM) to model individual differences, which is the topic of this paper. In particular, we developed a modeling approach using data collected from players playing a Role-Playing Game (RPG). Our proposed approach is two fold: 1. We present a Hidden Markov Model (HMM) of player in-game behaviors to model individual differences, and 2. using the output of the HMM, we generate behavioral features used to classify real world players’ characteristics, including game expertise and the big five personality traits. Our results show predictive power for some of personality traits, such as game expertise and conscientiousness, but the most influential factor was game expertise.