I wanted to name this Adventures in Reinforcement Learning. Then I realized that it was probably the lamest name I could ever create. Wikipedia can explain it better. Then why do you even have a blog post? Well I had to take a graduate level AI class to understand Reinforcement Learning enough for me to try playing around with examples I found online and tweak them to my interests, ultimately creating something in an hour while listening to RetroWave.

This week Microsoft announced a new collaboration with Björk to create a series of musical compositions with a custom built artificial intelligence tool. The AI will create dynamic new variations of Björk's original arrangements based on the changing weather patterns and position of the sun . Called'Kórsafn,' which means'choir archive' in Icelandic, the composition will be played continuously in the lobby of Sister City, a hotel in New York's lower east side that opened in the spring of 2019. Björk has created a new AI-driven musical work, called'Kórsafn,' which will play in the lobby of New York's Sister City hotel in the lower east side Described as a'generative soundscape,' the composition combines sounds and motifs from Björk's personal of choir archives, which she has compiled over the last 17 years as a solo artist. 'Kórsafn' isn't just a series of old sound files, however, Björk revisited her old set of recordings and notes and samples to create a series of new set of arrangements just for the project.

School of the Built Environment, Oxford Brookes University, Oxford OX3 0BP, UK; a. mosavi@brookes.ac.uk Abstract: Prediction models in mobility and transportation maintenance systems have been dramatically improved through using machine learning methods . The traditional road inspecti on systems based on the pavement condition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, t he proposed models utilize surface deflection data from falling weight deflectometer (FWD) test s to predict the PC I. Machine learning methods are the single multi - layer perceptron (MLP) and radial basis function (RBF) neural networks as well their hybrids, i.e., L eve nberg - M arquardt (MLP - LM), scaled conjugate gradient (MLP - SCG), imperialist competitive (RBF - ICA), and g enetic algorithms (RBF - GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accur acy of the modeling. The results of the analysis have been verified through using four criteria of aver age percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE), and standard error (SD). The CMIS mode l outperforms other models with the promising results of APRE 2.3303, AAPRE 11.6768, RMSE 12.0056, and SD 0.0210. Introduction In road transportation, pavement plays a vital role as th e part of the road that is in direct contact with vehicles . U sers' judgment about the quality of road service is primarily predicated upon pavement conditions. The Maintena nce, Rehabilitation, and Reconstruction (MR&R) program of pavement network is a multidimensional decision - making process that takes into account several consideration s.

Artificial intelligence is already ubiquitous, and is increasingly being used to autonomously make ever more consequential decisions. However, there has been relatively little research into the consequences for equity of the use of narrow AI and automated decision systems in medicine and public health. A narrative review using a hermeneutic approach was undertaken to explore current and future uses of AI in medicine and public health, issues that have emerged, and longer-term implications for population health. Accounts in the literature reveal a tremendous expectation on AI to transform medical and public health practices, especially regarding precision medicine and precision public health. Automated decisions being made about disease detection, diagnosis, treatment, and health funding allocation have significant consequences for individual and population health and wellbeing. Meanwhile, it is evident that issues of bias, incontestability, and erosion of privacy have emerged in sensitive domains where narrow AI and automated decision systems are in common use. As the use of automated decision systems expands, it is probable that these same issues will manifest widely in medicine and public health applications. Bias, incontestability, and erosion of privacy are mechanisms by which existing social, economic and health disparities are perpetuated and amplified. The implication is that there is a significant risk that use of automated decision systems in health will exacerbate existing population health inequities. The industrial scale and rapidity with which automated decision systems can be applied to whole populations heightens the risk to population health equity. There is a need therefore to design and implement automated decision systems with care, monitor their impact over time, and develop capacities to respond to issues as they emerge.

Networks are widely used to model objects with interactions and have enabled various downstream applications. However, in the real world, network mining is often done on particular query sets of objects, which does not require the construction and computation of networks including all objects in the datasets. In this work, for the first time, we propose to address the problem of query-specific network construction, to break the efficiency bottlenecks of existing network mining algorithms and facilitate various downstream tasks. To deal with real-world massive networks with complex attributes, we propose to leverage the well-developed data cube technology to organize network objects w.r.t. their essential attributes. An efficient reinforcement learning algorithm is then developed to automatically explore the data cube structures and construct the optimal query-specific networks. With extensive experiments of two classic network mining tasks on different real-world large datasets, we show that our proposed cube2net pipeline is general, and much more effective and efficient in query-specific network construction, compared with other methods without the leverage of data cube or reinforcement learning.

This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model's training and generalization performance is examined, and limitations are discussed.

Control Barrier Functions (CBF) have been recently utilized in the design of provably safe feedback control laws for nonlinear systems. These feedback control methods typically compute the next control input by solving an online Quadratic Program (QP). Solving QP in real-time can be a computationally expensive process for resource constraint systems. In this work, we propose to use imitation learning to learn Neural Network-based feedback controllers which will satisfy the CBF constraints. In the process, we also develop a new class of High Order CBF for systems under external disturbances. We demonstrate the framework on a unicycle model subject to external disturbances, e.g., wind or currents.

Although theoretically appealing, Stochastic Natural Gradient Des cent (SNGD) [1] is computationally expensive, it has been shown to be highly sensitiv e to the learning rate, and it is not guaranteed to be convergent. Converg ent Stochastic Natural Gradient Descent (CSNGD) [6] aims at solving the last two pr oblems. However, the computational expense of CSNGD is still unacceptab le when the number of parameters is large. In this paper we introduce the Dual Stochastic Natural Gradient Descent (DSNGD) where we take benefit of dually flat manifolds to obtain a robust alternative to SNGD which is also computation ally feasible. We start by reviewing dually flat manifold concepts in section 3. Then w e introduce exponential XY families, the mathematical model required for the application of DSNGD, in section 4. After that, in section 5 we introduce DSNGD in exponential XY families under a minimal parameterization. The same idea can be extended to exponential XY families which are overparameterized.

Actor critic methods with sparse rewards in model-based deep reinforcement learning typically require a deterministic binary reward function that reflects only two possible outcomes: if, for each step, the goal has been achieved or not. Our hypothesis is that we can influence an agent to learn faster by applying an external environmental pressure during training, which adversely impacts its ability to get higher rewards. As such, we deviate from the classical paradigm of sparse rewards and add a uniformly sampled reward value to the baseline reward to show that (1) sample efficiency of the training process can be correlated to the adversity experienced during training, (2) it is possible to achieve higher performance in less time and with less resources, (3) we can reduce the performance variability experienced seed over seed, (4) there is a maximum point after which more pressure will not generate better results, and (5) that random positive incentives have an adverse effect when using a negative reward strategy, making an agent under those conditions learn poorly and more slowly. These results have been shown to be valid for Deep Deterministic Policy Gradients using Hindsight Experience Replay in a well known Mujoco environment, but we argue that they could be generalized to other methods and environments as well.

A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints Marek Smieja a,, Łukasz Struski a, Mário A. T. Figueiredo b a Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland b Instituto de T elecomunicações, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, PortugalAbstract In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints. In contrast to existing approaches, we decompose SSC into two simpler classification tasks/stages: the first stage uses a pair of Siamese neural networks to label the unlabeled pairs of points as must-link or cannot-link; the second stage uses the fully pairwise-labeled dataset produced by the first stage in a supervised neural-network-based clustering method. The proposed approach, S 3 C 2 (Semi-Supervised Siamese C lassifiers for C lustering), is motivated by the observation that binary classification (such as assigning pairwise relations) is usually easier than multi-class clustering with partial supervision. On the other hand, being classification-based, our method solves only well-defined classification problems, rather than less well specified clustering tasks. Extensive experiments on various datasets demonstrate the high performance of the proposed method. Keywords: semi-supervised clustering, deep learning, neural networks, pairwise constraints 1. Introduction Clustering is an important unsupervised learning tool often used to analyze the structure of complex high-dimensional data. Semi-supervised clustering (SSC) methods tackle this issue by leveraging partial prior information about class labels, with the goal of obtaining partitions that are better aligned with true classes [1, 2, 3, 4, 5, 6]. One typical way of injecting class label information into clustering is in the form of pairwise constraints (typically, must-link and cannot-link constraints), or pairwise preferences (e.g., should-link and shouldn't-link), which indicate whether a given pair of points is believed to belong to the same or different classes. Most SSC approaches rely on adapting existing unsupervised clustering methods to handle partial (namely, pairwise) information [7, 8, 4, 5, 6, 9]. This requires transferring class-label knowledge into a clustering algorithm, which is often unnatural and puts a higher weight on clustering structure than on class labels.