Artificial intelligence (AI), machine learning (ML), and deep neural networks (DNNs) are the talk of the town these days. However, few people understand the difference between these innovative technologies. Artificial intelligence is an overarching concept that comprises several fields of computer science. It is geared toward solving tasks intrinsic to the human mind, such as speech recognition and object classification. Machine learning is part of the artificial intelligence ecosystem.

Recurrent neural networks have led to breakthroughs in natural language processing and speech recognition. Here we show that recurrent networks, specifically long short-term memory networks can also capture the temporal evolution of chemical/biophysical trajectories. Our character-level language model learns a probabilistic model of 1-dimensional stochastic trajectories generated from higher-dimensional dynamics. The model captures Boltzmann statistics and also reproduces kinetics across a spectrum of timescales. We demonstrate how training the long short-term memory network is equivalent to learning a path entropy, and that its embedding layer, instead of representing contextual meaning of characters, here exhibits a nontrivial connectivity between different metastable states in the underlying physical system. We demonstrate our model’s reliability through different benchmark systems and a force spectroscopy trajectory for multi-state riboswitch. We anticipate that our work represents a stepping stone in the understanding and use of recurrent neural networks for understanding the dynamics of complex stochastic molecular systems. Artificial neural networks have been successfully used for language recognition. Tsai et al. use the same techniques to link between language processing and prediction of molecular trajectories and show capability to predict complex thermodynamics and kinetics arising in chemical or biological physics.

At the #universityofoxford I focus a lot on the mathematics aspect of AI   I recommend eight books for the mathematics of AI     The Nature Of Statistical Le…

It can be difficult to assess the quality of a fitted model when facing unsupervised learning problems. Latent variable models, such as variation autoencoders and Gaussian mixture models, are often trained with likelihood-based approaches. In scope of Goodhart's law, when a metric becomes a target it ceases to be a good metric and therefore we should not use likelihood to assess the quality of the fit of these models. The solution we propose is a new metric for model comparison or regularization that relies on moments. The concept is to study the difference between the data moments and the model moments using a matrix norm, such as the Frobenius norm. We show how to use this new metric for model comparison and then for regularization. It is common to draw samples from the fitted distribution when evaluating latent variable models and we show that our proposed metric is faster to compute and has a smaller variance that this alternative. We conclude this article with a proof of concept of both applications and we discuss future work.

This paper introduces deep synoptic Monte Carlo planning (DSMCP) for large imperfect information games. The algorithm constructs a belief state with an unweighted particle filter and plans via playouts that start at samples drawn from the belief state. The algorithm accounts for uncertainty by performing inference on "synopses," a novel stochastic abstraction of information states. DSMCP is the basis of the program Penumbra, which won the official 2020 reconnaissance blind chess competition versus 33 other programs. This paper also evaluates algorithm variants that incorporate caution, paranoia, and a novel bandit algorithm. Furthermore, it audits the synopsis features used in Penumbra with per-bit saliency statistics.

We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action sequences in which goals generate sequences of high-level subtask descriptions, and these descriptions generate sequences of low-level actions. We describe how to train this model using primarily unannotated demonstrations by parsing demonstrations into sequences of named high-level subtasks, using only a small number of seed annotations to ground language in action. In trained models, the space of natural language commands indexes a combinatorial library of skills; agents can use these skills to plan by generating high-level instruction sequences tailored to novel goals. We evaluate this approach in the ALFRED household simulation environment, providing natural language annotations for only 10% of demonstrations. It completes more than twice as many tasks as a standard approach to learning from demonstrations, matching the performance of instruction following models with access to ground-truth plans during both training and evaluation.

Explaining predictions from Bayesian networks, for example to physicians, is non-trivial. Various explanation methods for Bayesian network inference have appeared in literature, focusing on different aspects of the underlying reasoning. While there has been a lot of technical research, there is very little known about how well humans actually understand these explanations. In this paper, we present ongoing research in which four different explanation approaches were compared through a survey by asking a group of human participants to interpret the explanations.

We investigate a clustering problem with data from a mixture of Gaussians that share a common but unknown, and potentially ill-conditioned, covariance matrix. We start by considering Gaussian mixtures with two equally-sized components and derive a Max-Cut integer program based on maximum likelihood estimation. We prove its solutions achieve the optimal misclassification rate when the number of samples grows linearly in the dimension, up to a logarithmic factor. However, solving the Max-cut problem appears to be computationally intractable. To overcome this, we develop an efficient spectral algorithm that attains the optimal rate but requires a quadratic sample size. Although this sample complexity is worse than that of the Max-cut problem, we conjecture that no polynomial-time method can perform better. Furthermore, we gather numerical and theoretical evidence that supports the existence of a statistical-computational gap. Finally, we generalize the Max-Cut program to a $k$-means program that handles multi-component mixtures with possibly unequal weights. It enjoys similar optimality guarantees for mixtures of distributions that satisfy a transportation-cost inequality, encompassing Gaussian and strongly log-concave distributions.

The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to facilitate, e.g., drawing multiple samples, sampling from structured domains, or gradient estimation for error backpropagation in neural network optimization. The goal of this survey article is to present background about the Gumbel-max trick, and to provide a structured overview of its extensions to ease algorithm selection. Moreover, it presents a comprehensive outline of (machine learning) literature in which Gumbel-based algorithms have been leveraged, reviews commonly-made design choices, and sketches a future perspective.

This PhD thesis contains several contributions to the field of statistical causal modeling. Statistical causal models are statistical models embedded with causal assumptions that allow for the inference and reasoning about the behavior of stochastic systems affected by external manipulation (interventions). This thesis contributes to the research areas concerning the estimation of causal effects, causal structure learning, and distributionally robust (out-of-distribution generalizing) prediction methods. We present novel and consistent linear and non-linear causal effects estimators in instrumental variable settings that employ data-dependent mean squared prediction error regularization. Our proposed estimators show, in certain settings, mean squared error improvements compared to both canonical and state-of-the-art estimators. We show that recent research on distributionally robust prediction methods has connections to well-studied estimators from econometrics. This connection leads us to prove that general K-class estimators possess distributional robustness properties. We, furthermore, propose a general framework for distributional robustness with respect to intervention-induced distributions. In this framework, we derive sufficient conditions for the identifiability of distributionally robust prediction methods and present impossibility results that show the necessity of several of these conditions. We present a new structure learning method applicable in additive noise models with directed trees as causal graphs. We prove consistency in a vanishing identifiability setup and provide a method for testing substructure hypotheses with asymptotic family-wise error control that remains valid post-selection. Finally, we present heuristic ideas for learning summary graphs of nonlinear time-series models.