Travis Jefferies is a Staff AI Research Engineer in the Lockheed Artificial Intelligence Center (LAIC). In this role, he is an individual contributor on an AI consulting team that is tasked with solving problems and proliferating AI adoption to Lockheed Martin business areas. Prior to his role in the LAIC, Travis worked in Sustainment where he used analytics and machine learning to help automate manual processes, reduce uncertainty, and achieve higher availability and mission capability for the warfighter. Travis is committed to lifelong learning and holds a Masters degree in Analytics from Georgia Tech and a Bachelors degree in Engineering Management from the University of Arizona. On the weekends he can be found barbequing, dancing, or summiting mountains in southern Arizona where he grew up and currently lives.

This course provides a comprehensive understanding of MobileNet, a state-of-the-art deep learning architecture for resource-constrained devices such as smartphones and IoT devices. MobileNet is optimized for real-time image and video classification, making it an ideal choice for cutting-edge computer vision applications. One of the key innovations in MobileNet is the use of depthwise separable convolutions, which allow for efficient computation and reduced memory footprint compared to traditional convolutional neural networks (CNNs). In this course, you'll learn about the computational costs of standard convolutions and how depthwise separable convolutions reduce computational overhead. In addition, you'll explore squeeze and excitation layers, which add a self-attention mechanism to the network, allowing it to focus on the most important features in an input image.

Learn how to use ChatGPT to build apps, fix bugs, and automate your workflow in Python or other programming languages. Created by Ardit Sulce 1.5 hours on-demand video course In this course, you will learn how to use ChatGPT to simplify and streamline your programming workflow. With ChatGPT's cutting-edge language processing capabilities, you will be able to build, fix, and add features to your programs with ease. If you know a programming language well, or if you have just started and are struggling to program, ChatGPT is there for you to make your life easier. This course is designed for all beginners, intermediate and advanced programmers who already have some programming experience and want to take their skills to the next level.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. A Texas woman accused of stabbing her online date in a Nevada hotel-casino in March 2022 for retaliation of the 2020 death of an Iranian military leader has been banned from attending classes at the University of Texas in Dallas while on house arrest, according to reports. Nika Nikoubin, 22, was charged with attempted murder, battery with a deadly weapon and burglary in March 2022, according to KLAS in Las Vegas. Nikoubin reportedly met a man on a dating website and the two rented a room together at the Sunset Station hotel.

Future AI applications require performance, reliability and privacy that the existing, cloud-dependant system architectures cannot provide. In this article, we study orchestration in the device-edge-cloud continuum, and focus on edge AI for resource orchestration. We claim that to support the constantly growing requirements of intelligent applications in the device-edge-cloud computing continuum, resource orchestration needs to embrace edge AI and emphasize local autonomy and intelligence. To justify the claim, we provide a general definition for continuum orchestration, and look at how current and emerging orchestration paradigms are suitable for the computing continuum. We describe certain major emerging research themes that may affect future orchestration, and provide an early vision of an orchestration paradigm that embraces those research themes. Finally, we survey current key edge AI methods and look at how they may contribute into fulfilling the vision of future continuum orchestration.

Pretrained language models have shown superior performance on many natural language processing tasks, yet they still struggle at multi-step formal reasoning tasks like grade school math problems. One key challenge of finetuning them to solve such math reasoning problems is that many existing datasets only contain one reference solution for each problem, despite the fact that there are often alternative solutions resembling different reasoning paths to the final answer. This way, the finetuned models are biased towards the limited reference solutions, which limits their generalization to unseen examples. To mitigate this issue, we propose to let the model perform sampling during training and learn from both self-sampled fully-correct solutions, which yield the correct answer upon execution, and partially-correct solutions, whose intermediate state matches an intermediate state of a known correct solution. We show that our use of self-sampled correct and partially-correct solutions can benefit learning and help guide the sampling process, leading to more efficient exploration of the solution space. Additionally, we explore various training objectives to support learning from multiple solutions per example and find they greatly affect the performance. Experiments on two math reasoning datasets show the effectiveness of our method compared to learning from a single reference solution with MLE, where we improve PASS@100 from 35.5% to 44.5% for GSM8K, and 27.6% to 36.2% PASS@80 for MathQA. Such improvements are also consistent across different model sizes. Our code is available at https://github.com/microsoft/TraceCodegen.

Despite progress in adversarial training (AT), there is a substantial gap between the top-performing and worst-performing classes in many datasets. For example, on CIFAR10, the accuracies for the best and worst classes are 74% and 23%, respectively. We argue that this gap can be reduced by explicitly optimizing for the worst-performing class, resulting in a min-max-max optimization formulation. Our method, called class focused online learning (CFOL), includes high probability convergence guarantees for the worst class loss and can be easily integrated into existing training setups with minimal computational overhead. We demonstrate an improvement to 32% in the worst class accuracy on CIFAR10, and we observe consistent behavior across CIFAR100 and STL10. Our study highlights the importance of moving beyond average accuracy, which is particularly important in safety-critical applications.

Existing research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers. There is a limited understanding of how AI may perform in group decision-making. This paper presents a wizard-of-oz study in which two participants and an AI form a committee to rank three English essays. One novelty of our study is that we adopt a speculative design by endowing AI equal power to humans in group decision-making.We enable the AI to discuss and vote equally with other human members. We find that although the voice of AI is considered valuable, AI still plays a secondary role in the group because it cannot fully follow the dynamics of the discussion and make progressive contributions. Moreover, the divergent opinions of our participants regarding an "equal AI" shed light on the possible future of human-AI relations.

Reinforcement learning (RL) has been extensively researched for enhancing human-environment interactions in various human-centric tasks, including e-learning and healthcare. Since deploying and evaluating policies online are high-stakes in such tasks, off-policy evaluation (OPE) is crucial for inducing effective policies. In human-centric environments, however, OPE is challenging because the underlying state is often unobservable, while only aggregate rewards can be observed (students' test scores or whether a patient is released from the hospital eventually). In this work, we propose a human-centric OPE (HOPE) to handle partial observability and aggregated rewards in such environments. Specifically, we reconstruct immediate rewards from the aggregated rewards considering partial observability to estimate expected total returns. We provide a theoretical bound for the proposed method, and we have conducted extensive experiments in real-world human-centric tasks, including sepsis treatments and an intelligent tutoring system. Our approach reliably predicts the returns of different policies and outperforms state-of-the-art benchmarks using both standard validation methods and human-centric significance tests.

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adaptation network (MuFAN) that utilizes a richer context encoding extracted from different levels of a pre-trained network. Additionally, we introduce a novel structure-wise distillation loss and replace the commonly used batch normalization layer with a newly proposed stability-plasticity normalization module to train MuFAN that simultaneously maintains high plasticity and stability. MuFAN outperforms other state-of-the-art continual learning methods on the SVHN, CIFAR100, miniImageNet, and CORe50 datasets. Extensive experiments and ablation studies validate the significance and scalability of each proposed component: 1) multi-scale feature maps from a pre-trained encoder, 2) the structure-wise distillation loss, and 3) the stability-plasticity normalization module in MuFAN. Code is publicly available at https://github.com/whitesnowdrop/MuFAN.