Starting with our very first store on Ocean Avenue in San Francisco, opened almost 50 years ago by Doris and Don Fisher. The thread that's run through those five decades is the phenomenal people that make up our brand – our employees and our customers. People who are rooted in the Legacy that makes Gap what it is, but who are also focused on the future. People who want to leave the world better than they found it. We've built our brand on staying true to our roots while always being out in front of what's next. If you want to be part of an iconic American brand, and help lead the way for where we're headed, we'd love to have you join us About the Role* In this role, you will support the store leadership team by performing functional tasks as assigned. You will act as a mentor and role model to employees to support service behaviors and the execution of tasks in specific areas of expertise. You will focus on leading processes and/or areas of the business, executing tasks and maintaining productivity to ensure goals are met. Through collaboration with your leadership team, your goal is to teach and coach your team and drive behaviors to deliver a best-in-class customer experience What You'll Do* Serve as a role model to achieve priorities in store, with the customer as the primary focus Support the store leadership team to collaborate effectively with employees and ensure work tasks are completed in a timely and efficient manner Build and share expertise in an assigned specialized functional area Support completion or work processes before or after the store closes as needed inclusive of opening and/or closing the store Listen and ask questions to solicit feedback to understand needs and provide service Handle unique or complex customer interactions.Who You Are* Provides clear and direct communication of expectations and gives feedback Ability to utilize technology effectively and engage with customers and your team to meet goals Able to effectively lead and inspire others through coaching and mentoring Demonstrate interest and initiative towards continuous improvement and growth Research process or transaction flow to identify root cause of errors. One of the most competitive Paid Time Off plans in the industry.* Employees can take up to five "on the clock" hours each month to volunteer at a charity of their choice.

The multidisciplinary artist Nayland Blake was once a child gazing in wonder at Alexander Calder's "circus" in the lobby of the Whitney Museum. "Who's the circus now?" Blake said the other day, some fifty years later, gesturing around a conference room across from the museum's education center. Blake, bearish, Merlin-bearded, soft-spoken in the manner of a blacksmith teaching kindergartners, was preparing for a session in their performance series, "Got an Art Problem?," part of this year's Whitney Biennial. In June, Blake threw a "Gender Discard Party" in the museum's lobby, to which guests were invited to "bring your own baggage" and dance away the woes of classification, in view of the artist's "Rear Entry," a reproduction of the door to the Mineshaft, the former gay club in the meatpacking district. Blake thought the curators would never go for "Rear Entry."

Warehouse management has changed significantly in the past decade. The COVID-19 pandemic, greater consumer access to technology, and wider demand for delivery mean that firms like Amazon have seen a $12 billion jump in profits compared to pre-pandemic estimates. But meeting the increased demand placed on warehouses isn't easy. The sheer volume and speed of orders require digitally-integrated solutions at every level. A generous helping of artificial intelligence is also needed to ensure that everyone's orders arrive on time and in their intended state.

A reinforcement learning (RL) control policy could fail in a new/perturbed environment that is different from the training environment, due to the presence of dynamic variations. For controlling systems with continuous state and action spaces, we propose an add-on approach to robustifying a pre-trained RL policy by augmenting it with an $\mathcal{L}_{1}$ adaptive controller ($\mathcal{L}_{1}$AC). Leveraging the capability of an $\mathcal{L}_{1}$AC for fast estimation and active compensation of dynamic variations, the proposed approach can improve the robustness of an RL policy which is trained either in a simulator or in the real world without consideration of a broad class of dynamic variations. Numerical and real-world experiments empirically demonstrate the efficacy of the proposed approach in robustifying RL policies trained using both model-free and model-based methods.

Learning a control policy capable of adapting to time-varying and potentially evolving system dynamics has been a great challenge to the mainstream reinforcement learning (RL). Mainly, the ever-changing system properties would continuously affect how the RL agent interacts with the state space through its actions, which effectively (re-)introduces concept drifts to the underlying policy learning process. We postulated that higher adaptability for the control policy can be achieved by characterizing and representing actions with extra "degrees of freedom" and thereby, with greater flexibility, adjusts to variations from the action's "behavioral" outcomes, including how these actions get carried out in real time and the shift in the action set itself. This paper proposes a Bayesian-flavored generalized RL framework by first establishing the notion of parametric action model to better cope with uncertainty and fluid action behaviors, followed by introducing the notion of reinforcement field as a physics-inspired construct established through "polarized experience particles" maintained in the RL agent's working memory. These particles effectively encode the agent's dynamic learning experience that evolves over time in a self-organizing way. Using the reinforcement field as a substrate, we will further generalize the policy search to incorporate high-level decision concepts by viewing the past memory as an implicit graph structure, in which the memory instances, or particles, are interconnected with their degrees of associability/similarity defined and quantified such that the "associative memory" principle can be consistently applied to establish and augment the learning agent's evolving world model.

When an agent encounters a continual stream of new tasks in the lifelong learning setting, it leverages the knowledge it gained from the earlier tasks to help learn the new tasks better. In such a scenario, identifying an efficient knowledge representation becomes a challenging problem. Most research works propose to either store a subset of examples from the past tasks in a replay buffer, dedicate a separate set of parameters to each task or penalize excessive updates over parameters by introducing a regularization term. While existing methods employ the general task-agnostic stochastic gradient descent update rule, we propose a task-aware optimizer that adapts the learning rate based on the relatedness among tasks. We utilize the directions taken by the parameters during the updates by additively accumulating the gradients specific to each task. These task-based accumulated gradients act as a knowledge base that is maintained and updated throughout the stream. We empirically show that our proposed adaptive learning rate not only accounts for catastrophic forgetting but also exhibits knowledge transfer. We also show that our method performs better than several state-of-the-art methods in lifelong learning on complex datasets. Moreover, our method can also be combined with the existing methods and achieve substantial improvement in performance. Lifelong learning (LLL), also known as continual learning, is a setting where an agent continuously learns from data belonging to different tasks (Parisi et al., 2019). Here, the goal is to maximize performance on all the tasks arriving in a stream without replaying the entire datasets from past tasks (Riemer et al., 2018). Approaches proposed in this setting involve investigating the stability-plasticity dilemma (Mermillod et al., 2013) in different ways where stability refers to preventing the forgetting of past knowledge and plasticity refers to accumulating new knowledge by learning new tasks (Mermillod et al., 2013; Delange et al., 2021). 1 Unlike human beings, who can efficiently assess the correctness and applicability of the past knowledge (Chen & Liu, 2018), neural networks and other machine learning models often face various issues in this setting. Whenever data from a new task arrives, these models often tend to forget the previously obtained knowledge due to dependency on the input data distribution, limited capacity, diversity among tasks, etc.

In this paper we present a general framework for estimating regression models subject to a user-defined level of fairness. We enforce fairness as a model selection step in which we choose the value of a ridge penalty to control the effect of sensitive attributes. We then estimate the parameters of the model conditional on the chosen penalty value. Our proposal is mathematically simple, with a solution that is partly in closed form, and produces estimates of the regression coefficients that are intuitive to interpret as a function of the level of fairness. Furthermore, it is easily extended to generalised linear models, kernelised regression models and other penalties; and it can accommodate multiple definitions of fairness. We compare our approach with the regression model from Komiyama et al. (2018), which implements a provably-optimal linear regression model; and with the fair models from Zafar et al. (2019). We evaluate these approaches empirically on six different data sets, and we find that our proposal provides better goodness of fit and better predictive accuracy for the same level of fairness. In addition, we highlight a source of bias in the original experimental evaluation in Komiyama et al. (2018).

Abstract--Learning-based visual ego-motion estimation is promising yet not ready for navigating agile mobile robots in the real world. In this article, we propose CUAHN-VIO, a robust and efficient monocular visual-inertial odometry (VIO) designed for micro aerial vehicles (MAVs) equipped with a downward-facing camera. The vision frontend is a content-anduncertainty-aware homography network (CUAHN) that is robust to non-homography image content and failure cases of network prediction. It not only predicts the homography transformation but also estimates its uncertainty. The training is self-supervised, so that it does not require ground truth that is often difficult to obtain. The network has good generalization that enables "plugand-play" deployment in new environments without fine-tuning. A lightweight extended Kalman filter (EKF) serves as the VIO backend and utilizes the mean prediction and variance estimation from the network for visual measurement updates. CUAHN-VIO is evaluated on a high-speed public dataset and shows rivaling accuracy to state-of-the-art (SOTA) VIO approaches. Visualized outputs of CUAHN-VIO evaluated on Seq. 13 of the UZH-processor to navigate a fast autonomous MAV. CUAHN is robust to sparse non-planar objects and motion blur. The arrows in pink are the networkpredicted optical flow vectors of the four corner pixels. They are plotted according to the uncertainty estimation from the network. The code developed for CUAHN-VIO will be open-sourced at the same link upon the publication of this article. A video of VIO runtime have inherent defects. They are often affected by disadvantageous performance is available at https://youtu.be/ NgDkgON-nE. An alternative is learning to predict camera ego-motion by a deep neural network (DNN). HANKS to the rapid development of computer vision and state estimation techniques, VIO has become a DNNs better cope with visually degraded conditions than their trustworthy component of autonomous robots, such as MAVs.

The widespread adoption of handheld devices have fueled rapid growth in new applications. Several of these new applications employ machine learning models to train on user data that is typically private and sensitive. Federated Learning enables machine learning models to train locally on each handheld device while only synchronizing their neuron updates with a server. While this enables user privacy, technology scaling and software advancements have resulted in handheld devices with varying performance capabilities. This results in the training time of federated learning tasks to be dictated by a few low-performance straggler devices, essentially becoming a bottleneck to the entire training process. In this work, we aim to mitigate the performance bottleneck of federated learning by dynamically forming sub-models for stragglers based on their performance and accuracy feedback. To this end, we offer the Invariant Dropout, a dynamic technique that forms a sub-model based on the neuron update threshold. Invariant Dropout uses neuron updates from the non-straggler clients to develop a tailored sub-models for each straggler during each training iteration. All corresponding weights which have a magnitude less than the threshold are dropped for the iteration. We evaluate Invariant Dropout using five real-world mobile clients. Our evaluations show that Invariant Dropout obtains a maximum accuracy gain of 1.4% points over state-of-the-art Ordered Dropout while mitigating performance bottlenecks of stragglers.

Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially relevant time-frequency bins in a spectrogram or time-pitch bins in a piano roll. This can be difficult to understand, particularly for musicologists without technical knowledge. To address this issue, we focus on more human-friendly explanations based on high-level musical concepts. Our research targets trained systems (post-hoc explanations) and explores two approaches: a supervised one, where the user can define a musical concept and test if it is relevant to the system; and an unsupervised one, where musical excerpts containing relevant concepts are automatically selected and given to the user for interpretation. We demonstrate both techniques on an existing symbolic composer classification system, showcase their potential, and highlight their intrinsic limitations.