Fargo represents the next step in Wells Fargo's digital transformation, which began last year with the announcement of a 10-year plan to modernize its cloud infrastructure with Microsoft and Google. A statement Monday from the 170-year-old bank said it plans to "become digital-first and reinvent personal finance." "This partnership will expand our customers' digital financial support network by enabling meaningful money conversations conveniently from their mobile device," said Michelle Moore, Wells Fargo's head of digital. "It's more than just dollars and cents; it's about uplifting our customers' emotional and financial well-being by understanding their financial goals and providing the most convenient interactions to meet those goals." Fargo will use Dialogflow, Google's conversational AI platform, to allow the virtual assistant to provide a tailored response to customers based on their intent, according to Monday's announcement.

Interactive Imitation Learning (IIL) is a branch of Imitation Learning (IL) where human feedback is provided intermittently during robot execution allowing an online improvement of the robot's behavior. In recent years, IIL has increasingly started to carve out its own space as a promising data-driven alternative for solving complex robotic tasks. The advantages of IIL are its data-efficient, as the human feedback guides the robot directly towards an improved behavior, and its robustness, as the distribution mismatch between the teacher and learner trajectories is minimized by providing feedback directly over the learner's trajectories. Nevertheless, despite the opportunities that IIL presents, its terminology, structure, and applicability are not clear nor unified in the literature, slowing down its development and, therefore, the research of innovative formulations and discoveries. In this article, we attempt to facilitate research in IIL and lower entry barriers for new practitioners by providing a survey of the field that unifies and structures it. In addition, we aim to raise awareness of its potential, what has been accomplished and what are still open research questions. We organize the most relevant works in IIL in terms of human-robot interaction (i.e., types of feedback), interfaces (i.e., means of providing feedback), learning (i.e., models learned from feedback and function approximators), user experience (i.e., human perception about the learning process), applications, and benchmarks. Furthermore, we analyze similarities and differences between IIL and RL, providing a discussion on how the concepts offline, online, off-policy and on-policy learning should be transferred to IIL from the RL literature. We particularly focus on robotic applications in the real world and discuss their implications, limitations, and promising future areas of research.

In September 2016, Stanford's "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the first report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society. It was written by a panel of 17 study authors, each of whom is deeply rooted in AI research, chaired by Peter Stone of the University of Texas at Austin. The report, entitled "Artificial Intelligence and Life in 2030," examines eight domains of typical urban settings on which AI is likely to have impact over the coming years: transportation, home and service robots, healthcare, education, public safety and security, low-resource communities, employment and workplace, and entertainment. It aims to provide the general public with a scientifically and technologically accurate portrayal of the current state of AI and its potential and to help guide decisions in industry and governments, as well as to inform research and development in the field. The charge for this report was given to the panel by the AI100 Standing Committee, chaired by Barbara Grosz of Harvard University.

Clicks on rankings suffer from position-bias: generally items on lower ranks are less likely to be examined - and thus clicked - by users, in spite of their actual preferences between items. The prevalent approach to unbiased click-based learning-to-rank (LTR) is based on counterfactual inverse-propensity-scoring (IPS) estimation. In contrast with general reinforcement learning, counterfactual doubly-robust (DR) estimation has not been applied to click-based LTR in previous literature. In this paper, we introduce a novel DR estimator that is the first DR approach specifically designed for position-bias. The difficulty with position-bias is that the treatment - user examination - is not directly observable in click data. As a solution, our estimator uses the expected treatment per rank, instead of the actual treatment that existing DR estimators use. Our novel DR estimator has more robust unbiasedness conditions than the existing IPS approach, and in addition, provides enormous decreases in variance: our experimental results indicate it requires several orders of magnitude fewer datapoints to converge at optimal performance. For the unbiased LTR field, our DR estimator contributes both increases in state-of-the-art performance and the most robust theoretical guarantees of all known LTR estimators.

Recommender systems suffer from the cold-start problem whenever a new user joins the platform or a new item is added to the catalog. To address item cold-start, we propose to replace the embedding layer in sequential recommenders with a dynamic storage that has no learnable weights and can keep an arbitrary number of representations. In this paper, we present FELRec, a large embedding network that refines the existing representations of users and items in a recursive manner, as new information becomes available. In contrast to similar approaches, our model represents new users and items without side information or time-consuming fine-tuning. During item cold-start, our method outperforms similar method by 29.50%-47.45%. Further, our proposed model generalizes well to previously unseen datasets. The source code is publicly available at github.com/kweimann/FELRec.

An expert on voice recognition and speech technologies responds to Ysabelle Cheung's "Galatea." When Joseph Faber invented the Euphonia, a mid-19th century analog voice synthesizer, people weren't impressed. They found Faber's invention to be a strange device with little to no purpose. In an attempt to create a machine that could mimic human speech, Faber was physically tethered to his invention, manipulating its bellows, gears, and hardware to produce human-like utterances--from short speeches to ghostly renditions of "God Save the Queen"--with a flat affect. One version of the machine was designed with a feminine face attached to its bellows, hair in ringlets and fair, smooth-looking skin.

People have been afraid that AI will make humans obsolete since its introduction to the workforce. We began to see AI take over jobs and cause layoffs in certain industries like the automotive industry. Although this only fuelled the anti-AI firestorm, it may have been a mistake. According to current trends, AI seems more likely to create jobs than take over. We keep you informed about current trends in the job marketplace.

Many real world person-person or person-product relationships can be modeled graphically. More specifically, bipartite graphs can be especially useful when modeling scenarios that involve two disjoint groups. As a result, many existing papers have utilized bipartite graphs for the classical link recommendation problem. In this paper, using the principle of bipartite graphs, we present another approach to this problem with a two step algorithm that takes into account frequency and similarity between common edges to make recommendations. We test this approach with bipartite data gathered from the Epinions and Movielens data sources, and find it to perform with roughly 14 percent error, which improves upon baseline results. This is a promising result, and can be refined to generate even more accurate recommendations.

Recommendation systems have illustrated the significant progress made in characterizing users' preferences based on their past behaviors. Despite the effectiveness of recommending accurately, there exist several factors that are essential but unexplored for evaluating various facets of recommendation systems, e.g., fairness, diversity, and limited resources. To address these issues, we propose Track2Vec, a GPU-free customizable-driven framework for fairness music recommendation. In order to take both accuracy and fairness into account, our solution consists of three modules, a customized fairness-aware groups for modeling different features based on configurable settings, a track representation learning module for learning better user embedding, and an ensemble module for ranking the recommendation results from different track representation learning modules. Moreover, inspired by TF-IDF which has been widely used in natural language processing, we introduce a metric called Miss Rate - Inverse Ground Truth Frequency (MR-ITF) to measure the fairness. Extensive experiments demonstrate that our model achieves a 4th price ranking in a GPU-free environment on the leaderboard in the EvalRS @ CIKM 2022 challenge, which is superior to the official baseline by about 200% in terms of the official scores. In addition, the ablation study illustrates the necessity of ensembling each group to acquire both accurate and fair recommendations.

We propose a recommendation system that suggests treatment strategies to a therapist during the psychotherapy session in real-time. Our system uses a turn-level rating mechanism that predicts the therapeutic outcome by computing a similarity score between the deep embedding of a scoring inventory, and the current sentence that the patient is speaking. The system automatically transcribes a continuous audio stream and separates it into turns of the patient and of the therapist and perform real-time inference of their therapeutic working alliance. The dialogue pairs along with their computed working alliance as ratings are then fed into a deep reinforcement learning recommendation system where the sessions are treated as users and the topics are treated as items. Other than evaluating the empirical advantages of the core components on an existing dataset of psychotherapy sessions, we demonstrate the effectiveness of this system in a web app.