Human intelligence is characterized by a remarkable ability to infer abstract rules from experience and apply these rules to novel domains. As such, designing neural network algorithms with this capacity is an important step toward the development of deep learning systems with more human-like intelligence. However, doing so is a major outstanding challenge, one that some argue will require neural networks to use explicit symbol-processing mechanisms. In this work, we focus on neural networks' capacity for arbitrary role-filler binding, the ability to associate abstract "roles" to context-specific "fillers," which many have argued is an important mechanism underlying the ability to learn and apply rules abstractly. Using a simplified version of Raven's Progressive Matrices, a hallmark test of human intelligence, we introduce a sequential formulation of a visual problem-solving task that requires this form of binding. Further, we introduce the Emergent Symbol Binding Network (ESBN), a recurrent neural network model that learns to use an external memory as a binding mechanism. This mechanism enables symbol-like variable representations to emerge through the ESBN's training process without the need for explicit symbol-processing machinery. We empirically demonstrate that the ESBN successfully learns the underlying abstract rule structure of our task and perfectly generalizes this rule structure to novel fillers.

In model serving, having one fixed model during the entire often life-long inference process is usually detrimental to model performance, as data distribution evolves over time, resulting in lack of reliability of the model trained on historical data. It is important to detect changes and retrain the model in time. The existing methods generally have three weaknesses: 1) using only classification error rate as signal, 2) assuming ground truth labels are immediately available after features from samples are received and 3) unable to decide what data to use to retrain the model when change occurs. We address the first problem by utilizing six different signals to capture a wide range of characteristics of data, and we address the second problem by allowing lag of labels, where labels of corresponding features are received after a lag in time. For the third problem, our proposed method automatically decides what data to use to retrain based on the signals. Extensive experiments on structured and unstructured data for different type of data changes establish that our method consistently outperforms the state-of-the-art methods by a large margin.

Current voice assistants typically use the best hypothesis yielded by their Automatic Speech Recognition (ASR) module as input to their Natural Language Understanding (NLU) module, thereby losing helpful information that might be stored in lower-ranked ASR hypotheses. We explore the change in performance of NLU associated tasks when utilizing five-best ASR hypotheses when compared to status quo for two language datasets, German and Portuguese. To harvest information from the ASR five-best, we leverage extractive summarization and joint extractive-abstractive summarization models for Domain Classification (DC) experiments while using a sequence-to-sequence model with a pointer generator network for Intent Classification (IC) and Named Entity Recognition (NER) multi-task experiments. For the DC full test set, we observe significant improvements of up to 7.2% and 15.5% in micro-averaged F1 scores, for German and Portuguese, respectively. In cases where the best ASR hypothesis was not an exact match to the transcribed utterance (mismatched test set), we see improvements of up to 6.7% and 8.8% micro-averaged F1 scores, for German and Portuguese, respectively. For IC and NER multi-task experiments, when evaluating on the mismatched test set, we see improvements across all domains in German and in 17 out of 19 domains in Portuguese (improvements based on change in SeMER scores). Our results suggest that the use of multiple ASR hypotheses, as opposed to one, can lead to significant performance improvements in the DC task for these non-English datasets. In addition, it could lead to significant improvement in the performance of IC and NER tasks in cases where the ASR model makes mistakes.

This paper considers the problem of computing Bayesian estimates of both states and model parameters for nonlinear state-space models. Generally, this problem does not have a tractable solution and approximations must be utilised. In this work, a variational approach is used to provide an assumed density which approximates the desired, intractable, distribution. The approach is deterministic and results in an optimisation problem of a standard form. Due to the parametrisation of the assumed density selected first- and second-order derivatives are readily available which allows for efficient solutions. The proposed method is compared against state-of-the-art Hamiltonian Monte Carlo in two numerical examples.

How often have you cursed out a traffic light that took forever to change? Or the lights on a long stretch of road made you stop at every cross street, just when you felt you might actually make it to work on time? Take heart: Less painful commutes may be ahead, with advanced electronic control systems that apply artificial intelligence to the task of keeping traffic moving. The benefits promised are more than just tamping down some road rage. Less time stuck in traffic, multiplied by many thousands of commuters, can lead to less fuel burned and less carbon emitted.

A spectrogram of the sound of a human voice, used by voice-recognition software. The idea of artificial intelligence (AI) -- systems so advanced they can mimic or outperform human cognition -- first came to prominence in 1950, when British computer scientist Alan Turing proposed an'imitation game' to assess whether a computer could fool humans into thinking they were communicating with another human. Soon after, researchers at Princeton University in New Jersey built MADALINE, the first artificial neural network applied to a real-world problem. Their system, modelled on the brain and nervous system, learnt to solve a maze through trial-and-error. Since then, the rise of AI has been enabled by exponentially faster and more powerful computers and large, complex data sets.

As from time to time it is impractical to ask agents to provide linear orders over all alternatives, for these partial rankings it is necessary to conduct preference completion. Specifically, the personalized preference of each agent over all the alternatives can be estimated with partial rankings from neighboring agents over subsets of alternatives. However, since the agents' rankings are nondeterministic, where they may provide rankings with noise, it is necessary and important to conduct the trustworthy preference completion. Hence, in this paper firstly, a trust-based anchor-kNN algorithm is proposed to find $k$-nearest trustworthy neighbors of the agent with trust-oriented Kendall-Tau distances, which will handle the cases when an agent exhibits irrational behaviors or provides only noisy rankings. Then, for alternative pairs, a bijection can be built from the ranking space to the preference space, and its certainty and conflict can be evaluated based on a well-built statistical measurement Probability-Certainty Density Function. Therefore, a certain common voting rule for the first $k$ trustworthy neighboring agents based on certainty and conflict can be taken to conduct the trustworthy preference completion. The properties of the proposed certainty and conflict have been studied empirically, and the proposed approach has been experimentally validated compared to state-of-arts approaches with several data sets.

Hyundai has agreed to buy an 80% stake in robot maker Boston Dynamics from SoftBank, the South Korean automaker said Friday. The deal values the robot firm at $1.1 billion, Hyundai said, suggesting it offered $880 million for the 80% stake. Boston Dynamics is best known for its robot dog, Spot, which went viral. Hyundai can leverage robot technology to expand automation at its unionized car factories, as well as design autonomous vehicles like self-driving cars, drones, and delivery robots, analysts said. Read more: The next big thing in classrooms: 'Zoom on wheels' robots are seeing a surge in demand The new stake comes after the newly promoted Hyundai Motor Group chairman, Euisun Chung, pledged to reduce reliance on traditional car manufacturing, saying car-making would only make up half of the company's future business.

Peter Hotez deceives New York Times readers about the odds of dying from measles in the US to persuade parents to comply with the CDC's vaccine schedule. On January 9, the New York Times published an article written by Dr. Peter J. Hotez titled "You Are Unvaccinated and Got Sick. His purpose in writing is to persuade parents to vaccinate their children according to the routine schedule recommended by the Centers for Disease Control and Prevention (CDC). To that end, he purports to compare "the dangerous effects of three diseases with the minimal side effects of their corresponding vaccines." "To state it bluntly," Hotez writes, "being unvaccinated can result in illness or death. Vaccines, in contrast, are extremely unlikely to lead to side effects, even minor ones like fainting." He laments that "vaccination rates have fallen", resulting in a resurgence of measles globally. He cites the example of Samoa, where "almost 5,700 measles cases have been recorded since September, resulting in at least 83 deaths. Almost all of those who died were young children." In the US, he writes, "vaccine hesitancy is contributing to" measles outbreaks. Hotez presents data ostensibly to enable parents "to compare the risks of becoming ill with measles . . . to the minute chances of experiencing side effects from their corresponding vaccines." Hotez goes on to assert, "Moreover, new research reveals that, even when patients recover, the measles virus can suppress the immune system, rendering children susceptible to serious infections like pneumonia and the flu." "misinformation spread after an article implying a link between measles vaccinations and autism was published in The Lancet in 1998; it was retracted in 2010 over concerns about the validity of the results and the conduct of the study.

"The tests demonstrated our success in applying artificial intelligence algorithms to'teach' the aircraft's brain to understand what is required of it," says …