Unmanned aerial vehicles (UAVs) have numerous applications, but their efficient and optimal flight can be a challenge. Reinforcement Learning (RL) has emerged as a promising approach to address this challenge, yet there is no standardized library for testing and benchmarking RL algorithms on UAVs. In this paper, we introduce PyFlyt, a platform built on the Bullet physics engine with native Gymnasium API support. PyFlyt provides modular implementations of simple components, such as motors and lifting surfaces, allowing for the implementation of UAVs of arbitrary configurations. Additionally, PyFlyt includes various task definitions and multiple reward function settings for each vehicle type. We demonstrate the effectiveness of PyFlyt by training various RL agents for two UAV models: quadrotor and fixed-wing. Our findings highlight the effectiveness of RL in UAV control and planning, and further show that it is possible to train agents in sparse reward settings for UAVs. PyFlyt fills a gap in existing literature by providing a flexible and standardised platform for testing RL algorithms on UAVs. We believe that this will inspire more standardised research in this direction.

This paper demonstrates the learning of the underlying device physics by mapping device structure images to their corresponding Current-Voltage (IV) characteristics using a novel framework based on variational autoencoders (VAE). Since VAE is used, domain expertise is not required and the framework can be quickly deployed on any new device and measurement. This is expected to be useful in the compact modeling of novel devices when only device cross-sectional images and electrical characteristics are available (e.g. novel emerging memory). Technology Computer-Aided Design (TCAD) generated and hand-drawn Metal-Oxide-Semiconductor (MOS) device images and noisy drain-current-gate-voltage curves (IDVG) are used for the demonstration. The framework is formed by stacking two VAEs (one for image manifold learning and one for IDVG manifold learning) which communicate with each other through the latent variables. Five independent variables with different strengths are used. It is shown that it can perform inverse design (generate a design structure for a given IDVG) and forward prediction (predict IDVG for a given structure image, which can be used for compact modeling if the image is treated as device parameters) successfully. Since manifold learning is used, the machine is shown to be robust against noise in the inputs (i.e. using hand-drawn images and noisy IDVG curves) and not confused by weak and irrelevant independent variables.

We study fair allocation of indivisible goods when agents have matroid rank valuations. Our main contribution is a simple algorithm based on the colloquial Yankee Swap procedure that computes provably fair and efficient Lorenz dominating allocations. While there exist polynomial time algorithms to compute such allocations, our proposed method improves on them in two ways. (a) Our approach is easy to understand and does not use complex matroid optimization algorithms as subroutines. (b) Our approach is scalable; it is provably faster than all known algorithms to compute Lorenz dominating allocations. These two properties are key to the adoption of algorithms in any real fair allocation setting; our contribution brings us one step closer to this goal.

In this article, we consider the manifold learning problem when the data set is invariant under the action of a compact Lie group $K$. Our approach consists in augmenting the data-induced graph Laplacian by integrating over the $K$-orbits of the existing data points, which yields a $K$-invariant graph Laplacian $L$. We prove that $L$ can be diagonalized by using the unitary irreducible representation matrices of $K$, and we provide an explicit formula for computing its eigenvalues and eigenfunctions. In addition, we show that the normalized Laplacian operator $L_N$ converges to the Laplace-Beltrami operator of the data manifold with an improved convergence rate, where the improvement grows with the dimension of the symmetry group $K$. This work extends the steerable graph Laplacian framework of Landa and Shkolnisky from the case of $\operatorname{SO}(2)$ to arbitrary compact Lie groups.

One of the keys to my success throughout the years has been my ability to understand technology. Innovation in digital marketing has been rapid but consistent… until now. As I'm watching artificial intelligence (AI) advancements, I fear that I'm falling behind… and it could cost me a great career where I've spent every spare minute studying, applying, and implementing with my customers. And, because it's AI, I know that once I fall behind, the machines will far outpace any chance I have of catching up. And I should disclose that I have one incredible edge over most business professionals, my son Bill is the Chief Data Scientist at OpenINSIGHTS with a PhD in Mathematics from the University of Illinois.

Fox News correspondent Matt Finn has the latest on the impact of AI technology that some say could outpace humans on'Special Report.' A college student in the U.K. said she was able to get out of a parking ticket by using AI technology to draft a letter requesting to revoke the fine. "I was like, 'Oh I don't need this fine, I'm a student' but trying to articulate what I wanted to say was pretty difficult so I thought I'll just see if ChatGPT can do it for me," the 22-year-old student in York, Millie Houlton, told the BBC. Houlton said she asked OpenAI's ChatGPT to "please help me write a letter to the council, they gave me a parking ticket." The ticket was for £60, or roughly $74, that the young woman said was wrongly issued after she parked on her street.

The current demand for pursuing a career in the field of AI and computer vision is at an all-time high. As with various other aspects of the digital realm, a comprehensive understanding of these areas can be attained through online resources. It is often presumed that the quality of online courses could be better than traditional methods, such as college-level programs, practical experience in the field, and offline studies. However, online learning has advanced beyond this misconception. Paid and free online courses can teach fundamental computer vision principles and specific elements of the discipline.

The ability to adapt to changing conditions is a key feature of a successful autonomous system. In this work, we use the Recursive Gaussian Processes (RGP) for identification of the quadrotor air drag model online, without the need of training data. The identified drag model then augments a physics-based model of the quadrotor dynamics, which allows more accurate quadrotor state prediction with increased ability to adapt to changing conditions. This data-augmented physics-based model is utilized for precise quadrotor trajectory tracking using the suitably modified Model Predictive Control (MPC) algorithm. The proposed modelling and control approach is evaluated using the Gazebo simulator and it is shown that the proposed approach tracks a desired trajectory with a higher accuracy compared to the MPC with the non-augmented (purely physics-based) model.

Many sequential decision-making problems that are currently automated, such as those in manufacturing or recommender systems, operate in an environment where there is either little uncertainty, or zero risk of catastrophe. As companies and researchers attempt to deploy autonomous systems in less constrained environments, it is increasingly important that we endow sequential decision-making algorithms with the ability to reason about uncertainty and risk. In this thesis, we will address both planning and reinforcement learning (RL) approaches to sequential decision-making. In the planning setting, it is assumed that a model of the environment is provided, and a policy is optimised within that model. Reinforcement learning relies upon extensive random exploration, and therefore usually requires a simulator in which to perform training. In many real-world domains, it is impossible to construct a perfectly accurate model or simulator. Therefore, the performance of any policy is inevitably uncertain due to the incomplete knowledge about the environment. Furthermore, in stochastic domains, the outcome of any given run is also uncertain due to the inherent randomness of the environment. These two sources of uncertainty are usually classified as epistemic, and aleatoric uncertainty, respectively. The over-arching goal of this thesis is to contribute to developing algorithms that mitigate both sources of uncertainty in sequential decision-making problems. We make a number of contributions towards this goal, with a focus on model-based algorithms...

The integration of machine learning models in various real-world applications is becoming more prevalent to assist humans in their daily decision-making tasks as a result of recent advancements in this field. However, it has been discovered that there is a tradeoff between the accuracy and fairness of these decision-making tasks. In some cases, these AI systems can be unfair by exhibiting bias or discrimination against certain social groups, which can have severe consequences in real life. Inspired by one of the most well-known human learning skills called grouping, we address this issue by proposing a novel machine learning framework where the ML model learns to group a diverse set of problems into distinct subgroups to solve each subgroup using its specific sub-model. Our proposed framework involves three stages of learning, which are formulated as a three-level optimization problem: (i) learning to group problems into different subgroups; (ii) learning group-specific sub-models for problem-solving; and (iii) updating group assignments of training examples by minimizing the validation loss. These three learning stages are performed end-to-end in a joint manner using gradient descent. To improve fairness and accuracy, we develop an efficient optimization algorithm to solve this three-level optimization problem. To further reduce the risk of overfitting in small datasets, we incorporate domain adaptation techniques in the second stage of training. We further apply our method to neural architecture search. Extensive experiments on various datasets demonstrate our method's effectiveness and performance improvements in both fairness and accuracy. Our proposed Learning by Grouping can reduce overfitting and achieve state-of-the-art performances with fixed human-designed network architectures and searchable network architectures on various datasets.