Applied category theory has recently developed libraries for computing with morphisms in interesting categories, while machine learning has developed ways of learning programs in interesting languages. Taking the analogy between categories and languages seriously, this paper defines a probabilistic generative model of morphisms in free monoidal categories over domain-specific generating objects and morphisms. The paper shows how acyclic directed wiring diagrams can model specifications for morphisms, which the model can use to generate morphisms. Amortized variational inference in the generative model then enables learning of parameters (by maximum likelihood) and inference of latent variables (by Bayesian inversion). A concrete experiment shows that the free category prior achieves competitive reconstruction performance on the Omniglot dataset.

This paper studies the cooperative learning of two generative flow models, in which the two models are iteratively updated based on the jointly synthesized examples. The first flow model is a normalizing flow that transforms an initial simple density into a target density by applying a sequence of invertible transformations. The second flow model is a Langevin flow that runs finite steps of gradient-based MCMC toward an energy-based model. We start from proposing a generative framework that trains an energy-based model with a normalizing flow as an amortized sampler to initialize the MCMC chains of the energy-based model. In each learning iteration, we generate synthesized examples by using a normalizing flow initialization followed by a short-run Langevin flow revision toward the current energy-based model. Then we treat the synthesized examples as fair samples from the energy-based model and update the model parameters with the maximum likelihood learning gradient, while the normalizing flow directly learns from the synthesized examples by maximizing the tractable likelihood. Under the short-run non-mixing MCMC scenario, the estimation of the energy-based model is shown to follow the perturbation of maximum likelihood, and the short-run Langevin flow and the normalizing flow form a two-flow generator that we call CoopFlow. We provide an understating of the CoopFlow algorithm by information geometry and show that it is a valid generator as it converges to a moment matching estimator. We demonstrate that the trained CoopFlow is capable of synthesizing realistic images, reconstructing images, and interpolating between images. Normalizing flows (Dinh et al., 2015; 2017; Kingma & Dhariwal, 2018) are a family of generative models that construct a complex distribution by transforming a simple probability density, such as Gaussian distribution, through a sequence of invertible and differentiable mappings. Due to the tractability of the exact log-likelihood and the efficiency of the inference and synthesis, normalizing flows have gained popularity in density estimation (Kingma & Dhariwal, 2018; Ho et al., 2019; Yang et al., 2019; Prenger et al., 2019; Kumar et al., 2020) and variational inference (Rezende & Mohamed, 2015; Kingma et al., 2016).

In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. To demonstrate the empirical efficiency of the proposed approaches we investigate their applications for decision making in recommender systems and energy systems domains. For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions. The proposed approach consists in minimizing pairwise ranking loss over blocks constituted by a sequence of non-clicked items followed by the clicked one for each user. We also explore the influence of long memory on the accurateness of predictions. SAROS shows highly competitive and promising results based on quality metrics and also it turn out faster in terms of loss convergence than stochastic gradient descent and batch classical approaches. Regarding power systems, we propose an algorithm for faulted lines detection based on focusing of misclassifications in lines close to the true event location. The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach based on convolutional neural networks for faults detection in power grid.

Abstract--Balancing the trade-off between safety and efficiency paths in uncertain environments, especially under nonconvex and is of significant importance for path planning under uncertainty. The initial paths are often of poor Many risk-aware path planners have been developed to explicitly quality as well. Therefore, we propose the NR-RRT algorithm limit the probability of collision to an acceptable bound in to rapidly find near-optimal solutions with guaranteed bounded uncertain environments. It utilizes an informed bidirectional search strategy after uncertainties are usually assumed to make the problem tractable having past experiences in those challenging environments. These assumptions limit the generalization RRT can be applied in not only seen but also unseen uncertain and application of path planners in real-world implementations. However, the algorithm cannot handle entirely unseen In this article, we propose to apply deep learning methods to environments that contain new or additional obstacles. In future the sampling-based planner, developing a novel risk bounded research, we will address the problem of planning under robot near-optimal path planning algorithm named neural risk-aware model uncertainty. Specifically, a deterministic risk contours map is Index Terms--Planning under uncertainty, Sampling-based maintained by perceiving the probabilistic nonconvex obstacles, path planning, Learning from demonstration. and a neural network sampler is proposed to predict the next most-promising safe state.

We introduce a conditional compression problem and propose a fast framework for tackling it. The problem is how to quickly compress a pretrained large neural network into optimal smaller networks given target contexts, e.g. a context involving only a subset of classes or a context where only limited compute resource is available. To solve this, we propose an efficient Bayesian framework to compress a given large network into much smaller size tailored to meet each contextual requirement. We employ a hypernetwork to parameterize the posterior distribution of weights given conditional inputs and minimize a variational objective of this Bayesian neural network. To further reduce the network sizes, we propose a new input-output group sparsity factorization of weights to encourage more sparseness in the generated weights. Our methods can quickly generate compressed networks with significantly smaller sizes than baseline methods.

This is an interesting paper that distils structure learning in Bayesian networks (BNs) and kernel methods in a quest to produce more flexible distributional assumptions. Conditional (linear) Gaussian Bayesian networks (CGBNs) have been well explored in the literature for some time, to the point that they now appear in many recent textbooks [1-3]. The authors address one of the key limitations of CGBNS, that they can only capture linear dependencies between the continuous variables they contain, and remove it by replacing (mixtures of) linear regression models with more general kernel densities. Dependencies between discrete variables were already flexible, because the conditional probability tables that parametrise them essentially act as a saturated model[4]. It is not obvious that more flexibility will produce better models for whatever task we have in mind: it can also lead to overfitting, instability and hyperparameter tuning problems.

Humanity has been waiting for self-driving cars for several decades. Thanks to the extremely fast evolution of technology, this idea recently went from "possible" to "commercially available in a Tesla". Deep learning is one of the main technologies that enabled self-driving. It's a versatile tool that can solve almost any problem – it can be used in physics, for example, the proton-proton collision in the Large Hadron Collider, just as well as in Google Lens to classify pictures. Deep learning is a technology that can help solve almost any type of science or engineering problem. CNN is the primary algorithm that these systems use to recognize and classify different parts of the road, and to make appropriate decisions. Along the way, we'll see how Tesla, Waymo, and Nvidia use CNN algorithms to make their cars driverless or autonomous. The first self-driving car was invented in 1989, it was the Automatic Land Vehicle in Neural Network (ALVINN). It used neural networks to detect lines, segment the environment, navigate itself, and drive. It worked well, but it was limited by slow processing powers and insufficient data.

This paper describes heavy-tailed extensions of a state-of-the-art versatile blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) from a unified point of view. The common way of deriving such an extension is to replace the multivariate complex Gaussian distribution in the likelihood function with its heavy-tailed generalization, e.g., the multivariate complex Student's t and leptokurtic generalized Gaussian distributions, and tailor-make the corresponding parameter optimization algorithm. Using a wider class of heavy-tailed distributions called a Gaussian scale mixture (GSM), i.e., a mixture of Gaussian distributions whose variances are perturbed by positive random scalars called impulse variables, we propose GSM-FastMNMF and develop an expectationmaximization algorithm that works even when the probability density function of the impulse variables have no analytical expressions. We show that existing heavy-tailed FastMNMF extensions are instances of GSM-FastMNMF and derive a new instance based on the generalized hyperbolic distribution that include the normal-inverse Gaussian, Student's t, and Gaussian distributions as the special cases. Our experiments show that the normalinverse Gaussian FastMNMF outperforms the state-of-the-art FastMNMF extensions and ILRMA model in speech enhancement and separation in terms of the signal-to-distortion ratio.

Autonomous systems that operate in the open world often use incomplete models of their environment. Model incompleteness is inevitable due to the practical limitations in precise model specification and data collection about open-world environments. Due to the limited fidelity of the model, agent actions may produce negative side effects (NSEs) when deployed. Negative side effects are undesirable, unmodeled effects of agent actions on the environment. NSEs are inherently challenging to identify at design time and may affect the reliability, usability and safety of the system. We present two complementary approaches to mitigate the NSE via: (1) learning from feedback, and (2) environment shaping. The solution approaches target settings with different assumptions and agent responsibilities. In learning from feedback, the agent learns a penalty function associated with a NSE. We investigate the efficiency of different feedback mechanisms, including human feedback and autonomous exploration. The problem is formulated as a multi-objective Markov decision process such that optimizing the agent’s assigned task is prioritized over mitigating NSE. A slack parameter denotes the maximum allowed deviation from the optimal expected reward for the agent’s task in order to mitigate NSE. In environment shaping, we examine how a human can assist an agent, beyond providing feedback, and utilize their broader scope of knowledge to mitigate the impacts of NSE. We formulate the problem as a human-agent collaboration with decoupled objectives. The agent optimizes its assigned task and may produce NSE during its operation. The human assists the agent by performing modest reconfigurations of the environment so as to mitigate the impacts of NSE, without affecting the agent’s ability to complete its assigned task. We present an algorithm for shaping and analyze its properties. Empirical evaluations demonstrate the trade-offs in the performance of different approaches in mitigating NSE in different settings.

In late December 2019, the novel coronavirus (Sars-Cov-2) and the resulting disease COVID-19 were first identified in Wuhan China. The disease slipped through containment measures, with the first known case in the United States being identified on January 20th, 2020. In this paper, we utilize survey data from the Inter-university Consortium for Political and Social Research and apply several statistical and machine learning models and techniques such as Decision Trees, Multinomial Logistic Regression, Naive Bayes, k-Nearest Neighbors, Support Vector Machines, Neural Networks, Random Forests, Gradient Tree Boosting, XGBoost, CatBoost, LightGBM, Synthetic Minority Oversampling, and Chi-Squared Test to analyze the impacts the COVID-19 pandemic has had on the mental health of frontline workers in the United States. Through the interpretation of the many models applied to the mental health survey data, we have concluded that the most important factor in predicting the mental health decline of a frontline worker is the healthcare role the individual is in (Nurse, Emergency Room Staff, Surgeon, etc.), followed by the amount of sleep the individual has had in the last week, the amount of COVID-19 related news an individual has consumed on average in a day, the age of the worker, and the usage of alcohol and cannabis.