This partnership suggests the chain is relying more heavily on AI and machine learning systems to improve its system. "Machine learning models can provide significant value to an organization in several business applications, but without a solid [machine learning] operations pipeline, that value cannot be truly realized," Zack Fragoso, manager, data science and AI at Domino's, said in the release. The chain began testing AI in 2018 with an Alexa-like voice recognition application called DOM. In 2019, Domino's began piloting Dragontail Systems' AI technology at its Australian and New Zealand locations to scan each pizza and ensure they measured up to quality standards. The pilot was expanded after improving quality scores by 15% in its first month.

We study liquid democracy, a collective decision making paradigm that allows voters to transitively delegate their votes, through an algorithmic lens. In our model, there are two alternatives, one correct and one incorrect, and we are interested in the probability that the majority opinion is correct. Our main question is whether there exist delegation mechanisms that are guaranteed to outperform direct voting, in the sense of being always at least as likely, and sometimes more likely, to make a correct decision. Even though we assume that voters can only delegate their votes to better-informed voters, we show that local delegation mechanisms, which only take the local neighborhood of each voter as input (and, arguably, capture the spirit of liquid democracy), cannot provide the foregoing guarantee. By contrast, we design a non-local delegation mechanism that does provably outperform direct voting under mild assumptions about voters.

Speaker recognition refers to audio biometrics that utilizes acoustic characteristics for automatic speaker recognition. These systems have emerged as an essential means of verifying identity in various scenarios, such as smart homes, general business interactions, e-commerce applications, and forensics. However, the mismatch between training and real-world data causes a shift of speaker embedding space and severely degrades the recognition performance. Various complicated neural architectures are presented to address speaker recognition in the wild but neglect the requirements of storage and computation. To address this issue, we propose a neural architecture search-based efficient time-delay neural network (EfficientTDNN) to improve inference efficiency while maintaining recognition accuracy. The proposed EfficientTDNN contains three phases. First, supernet design is to construct a dynamic neural architecture that consists of sequential cells and enables network pruning. Second, progressive training is to optimize randomly sampled subnets that inherit the weights of the supernet. Third, three search methods, including manual grid search, random search, and model predictive evolutionary search, are introduced to find a trade-off between accuracy and efficiency. Results of experiments on the VoxCeleb dataset show EfficientTDNN provides a huge search space including approximately $10^{13}$ subnets and achieves 1.66% EER and 0.156 DCF$_{0.01}$ with 565M MACs. Comprehensive investigation suggests that the trained supernet generalizes cells unseen during training and obtains an acceptable balance between accuracy and efficiency.

Prediction tasks about students have practical significance for both student and college. Making multiple predictions about students is an important part of a smart campus. For instance, predicting whether a student will fail to graduate can alert the student affairs office to take predictive measures to help the student improve his/her academic performance. With the development of information technology in colleges, we can collect digital footprints which encode heterogeneous behaviors continuously. In this paper, we focus on modeling heterogeneous behaviors and making multiple predictions together, since some prediction tasks are related and learning the model for a specific task may have the data sparsity problem. To this end, we propose a variant of LSTM and a soft-attention mechanism. The proposed LSTM is able to learn the student profile-aware representation from heterogeneous behavior sequences. The proposed soft-attention mechanism can dynamically learn different importance degrees of different days for every student. In this way, heterogeneous behaviors can be well modeled. In order to model interactions among multiple prediction tasks, we propose a co-attention mechanism based unit. With the help of the stacked units, we can explicitly control the knowledge transfer among multiple tasks. We design three motivating behavior prediction tasks based on a real-world dataset collected from a college. Qualitative and quantitative experiments on the three prediction tasks have demonstrated the effectiveness of our model.

Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is a key component of how humans understand, reason, and act in these worlds. However, it remains unclear to what extent artificial agents utilize semantic understanding of the text. To this end, we perform experiments to systematically reduce the amount of semantic information available to a learning agent. Surprisingly, we find that an agent is capable of achieving high scores even in the complete absence of language semantics, indicating that the currently popular experimental setup and models may be poorly designed to understand and leverage game texts. To remedy this deficiency, we propose an inverse dynamics decoder to regularize the representation space and encourage exploration, which shows improved performance on several games including Zork I. We discuss the implications of our findings for designing future agents with stronger semantic understanding.

Identifying the research topics that best describe the scope of a scientific publication is a crucial task for editors, in particular because the quality of these annotations determine how effectively users are able to discover the right content in online libraries. For this reason, Springer Nature, the world's largest academic book publisher, has traditionally entrusted this task to their most expert editors. These editors manually analyse all new books, possibly including hundreds of chapters, and produce a list of the most relevant topics. Hence, this process has traditionally been very expensive, time-consuming, and confined to a few senior editors. For these reasons, back in 2016 we developed Smart Topic Miner (STM), an ontology-driven application that assists the Springer Nature editorial team in annotating the volumes of all books covering conference proceedings in Computer Science. Since then STM has been regularly used by editors in Germany, China, Brazil, India, and Japan, for a total of about 800 volumes per year. Over the past three years the initial prototype has iteratively evolved in response to feedback from the users and evolving requirements. In this paper we present the most recent version of the tool and describe the evolution of the system over the years, the key lessons learnt, and the impact on the Springer Nature workflow. In particular, our solution has drastically reduced the time needed to annotate proceedings and significantly improved their discoverability, resulting in 9.3 million additional downloads. We also present a user study involving 9 editors, which yielded excellent results in term of usability, and report an evaluation of the new topic classifier used by STM, which outperforms previous versions in recall and F-measure.

The paper considers a distributed version of deep reinforcement learning (DRL) for multi-agent decision-making process in the paradigm of federated learning. Since the deep neural network models in federated learning are trained locally and aggregated iteratively through a central server, frequent information exchange incurs a large amount of communication overheads. Besides, due to the heterogeneity of agents, Markov state transition trajectories from different agents are usually unsynchronized within the same time interval, which will further influence the convergence bound of the aggregated deep neural network models. Therefore, it is of vital importance to reasonably evaluate the effectiveness of different optimization methods. Accordingly, this paper proposes a utility function to consider the balance between reducing communication overheads and improving convergence performance. Meanwhile, this paper develops two new optimization methods on top of variation-aware periodic averaging methods: 1) the decay-based method which gradually decreases the weight of the model's local gradients within the progress of local updating, and 2) the consensus-based method which introduces the consensus algorithm into federated learning for the exchange of the model's local gradients. This paper also provides novel convergence guarantees for both developed methods and demonstrates their effectiveness and efficiency through theoretical analysis and numerical simulation results.

Motivation: Several accurate deep learning models have been proposed to predict drug-target affinity (DTA). However, all of these models are black box hence are difficult to interpret and verify its result, and thus risking acceptance. Explanation is necessary to allow the DTA model more trustworthy. Explanation with counterfactual provides human-understandable examples. Most counterfactual explanation methods only operate on single input data, which are in tabular or continuous forms. In contrast, the DTA model has two discrete inputs. It is challenging for the counterfactual generation framework to optimize both discrete inputs at the same time. Results: We propose a multi-agent reinforcement learning framework, Multi-Agent Counterfactual Drug-target binding Affinity (MACDA), to generate counterfactual explanations for the drug-protein complex. Our proposed framework provides human-interpretable counterfactual instances while optimizing both the input drug and target for counterfactual generation at the same time. The result on the Davis dataset shows the advantages of the proposed MACDA framework compared with previous works.

It's something that many parents do without thinking, but if you use'baby talk' with your child, you may unknowingly be helping them to learn. A new study has revealed that babies really do prefer baby talk, and pay more attention to its exaggerated, sing-song tones. While previous research has shown that monolingual babies prefer baby talk, the new study found that it is also the case for babies exposed to two languages. Not only is it good to speak baby talk to engage an infant and help them learn, parents can use baby talk in two languages without making their offspring confused, the research reveals. Babies will pay more attention to baby talk than regular speech, regardless of which languages they're used to hearing, according to a study by UCLA's Language Acquisition Lab and 16 other labs around the world Baby talk is a certain style of speech employed by adults when talking to an infant.

When James Clarke went to work at London's legendary Abbey Road Studios in late 2009, he wasn't an audio engineer. He'd been hired to work as a software programmer. One day not long after he started, he was having lunch with several studio veterans of the 1960s and '70s, the pre-computer era of music recording when songs were captured on a single piece of tape. To make conversation, Clarke asked a seemingly innocent question: Could you take a tape from the days before multitrack recording and isolate the individual instruments? Could you pull it apart?