In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process,data from previous tasks cannot be stored and hence is not available when learning a new task. A critical issue in such context, not addressed in the literature so far, relates to the decision which expert to deploy at test time. We introduce a set of gating autoencoders that learn a representation for the task at hand, and, at test time, automatically forward the test sample to the relevant expert. This also brings memory efficiency as only one expert network has to be loaded into memory at any given time. Further, the autoencoders inherently capture the relatedness of one task to another, based on which the most relevant prior model to be used for training a new expert, with finetuning or learning without-forgetting, can be selected. We evaluate our method on image classification and video prediction problems.

This paper presents an end-to-end approach for tracking static and dynamic objects for an autonomous vehicle driving through crowded urban environments. Unlike traditional approaches to tracking, this method is learned end-to-end, and is able to directly predict a full unoccluded occupancy grid map from raw laser input data. Inspired by the recently presented DeepTracking approach [Ondruska, 2016], we employ a recurrent neural network (RNN) to capture the temporal evolution of the state of the environment, and propose to use Spatial Transformer modules to exploit estimates of the egomotion of the vehicle. Our results demonstrate the ability to track a range of objects, including cars, buses, pedestrians, and cyclists through occlusion, from both moving and stationary platforms, using a single learned model. Experimental results demonstrate that the model can also predict the future states of objects from current inputs, with greater accuracy than previous work.

A growing number of threats to Android phones creates challenges for malware detection. Manually labeling the samples into benign or different malicious families requires tremendous human efforts, while it is comparably easy and cheap to obtain a large amount of unlabeled APKs from various sources. Moreover, the fast-paced evolution of Android malware continuously generates derivative malware families. These families often contain new signatures, which can escape detection when using static analysis. These practical challenges can also cause traditional supervised machine learning algorithms to degrade in performance. In this paper, we propose a framework that uses model-based semi-supervised (MBSS) classification scheme on the dynamic Android API call logs. The semi-supervised approach efficiently uses the labeled and unlabeled APKs to estimate a finite mixture model of Gaussian distributions via conditional expectation-maximization and efficiently detects malwares during out-of-sample testing. We compare MBSS with the popular malware detection classifiers such as support vector machine (SVM), $k$-nearest neighbor (kNN) and linear discriminant analysis (LDA). Under the ideal classification setting, MBSS has competitive performance with 98\% accuracy and very low false positive rate for in-sample classification. For out-of-sample testing, the out-of-sample test data exhibit similar behavior of retrieving phone information and sending to the network, compared with in-sample training set. When this similarity is strong, MBSS and SVM with linear kernel maintain 90\% detection rate while $k$NN and LDA suffer great performance degradation. When this similarity is slightly weaker, all classifiers degrade in performance, but MBSS still performs significantly better than other classifiers.

Users form information trails as they browse the web, checkin with a geolocation, rate items, or consume media. A common problem is to predict what a user might do next for the purposes of guidance, recommendation, or prefetching. First-order and higher-order Markov chains have been widely used methods to study such sequences of data. First-order Markov chains are easy to estimate, but lack accuracy when history matters. Higher-order Markov chains, in contrast, have too many parameters and suffer from overfitting the training data. Fitting these parameters with regularization and smoothing only offers mild improvements. In this paper we propose the retrospective higher-order Markov process (RHOMP) as a low-parameter model for such sequences. This model is a special case of a higher-order Markov chain where the transitions depend retrospectively on a single history state instead of an arbitrary combination of history states. There are two immediate computational advantages: the number of parameters is linear in the order of the Markov chain and the model can be fit to large state spaces. Furthermore, by providing a specific structure to the higher-order chain, RHOMPs improve the model accuracy by efficiently utilizing history states without risks of overfitting the data. We demonstrate how to estimate a RHOMP from data and we demonstrate the effectiveness of our method on various real application datasets spanning geolocation data, review sequences, and business locations. The RHOMP model uniformly outperforms higher-order Markov chains, Kneser-Ney regularization, and tensor factorizations in terms of prediction accuracy.

In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test likelihood and faster convergence compared to regular full RNNs in most of our experiments. We show the benefits of using diagonal recurrent matrices with popularly used LSTM and GRU architectures as well as with the vanilla RNN architecture, on four standard symbolic music datasets.

Maximum likelihood estimation (MLE) is one of the most important methods in machine learning, and the expectation-maximization (EM) algorithm is often used to obtain maximum likelihood estimates. However, EM heavily depends on initial configurations and fails to find the global optimum. On the other hand, in the field of physics, quantum annealing (QA) was proposed as a novel optimization approach. Motivated by QA, we propose a quantum annealing extension of EM, which we call the deterministic quantum annealing expectation-maximization (DQAEM) algorithm. We also discuss its advantage in terms of the path integral formulation. Furthermore, by employing numerical simulations, we illustrate how it works in MLE and show that DQAEM outperforms EM.

SAN FRANCISCO, CA and QUEBEC, QC--(Marketwired - April 18, 2017) - Coveo, a recognized leader in AI-powered search and predictive analytics, and recently positioned as the highest for execution and furthest for innovation leader in the leaders quadrant of Gartner's Magic Quadrant for Insight Engines, has just announced the general availability of Coveo for Salesforce Free Edition. Coveo for Salesforce Free Edition now allows every brand using Salesforce to leverage Coveo's Machine Learning features and transform their self-service experiences to deliver more relevant content, at scale, whether for customers, partners or employees. Companies unintentionally make it difficult for people to find relevant content, let alone receiving relevant insights and personalized recommendations. It is even harder for community administrators and managers to gain valuable insights, and learn from usage and behavioral data, such as what customers are searching for, what drives better outcomes or what content gaps exist in their self-service pages. "Search and relevance are at the very core of user engagement, personalization and self-service success," said Laurent Simoneau, President and CTO of Coveo.

House finches based in North American cities and town are better at solving problems than rural ones. Researchers investigated how increased urbanization and human presence affects the behavior and foraging habits of birds. The findings suggests that city birds have become used to humans, but rural birds have not, so they perceive humans as threatening, interfering with their ability to problem solve. The house finch (Haemorhous mexicanus) is a songbird native to the desert areas of North America. It's found in urban and rural areas in Mexico, as well as the southwestern United States.

Daniel (Danny) Bobrow passed away peacefully at home with his wife Toni and daughters Kimberly and Deborah in Palo Alto, California, on March 20, 2017, having bravely fought a five-month battle with cancer. Danny was born to Ruth Gureasko Bobrow and Jacob Bobrow on November 29, 1935, in the Bronx, New York City. A gifted student, he attended Bronx High School of Science and went on to earn a BS from Rensselaer Polytechnic Institute, an MS from Harvard, and a PhD in Mathematics from Massachusetts Institute of Technology under the supervision of Marvin Minsky. His was one of the first MIT doctoral theses in Artificial Intelligence. A pioneer with a long and distinguished research career in Artificial Intelligence as a Research Fellow in the System Sciences Laboratory of the Palo Alto Research Center (PARC), he is remembered as a mentor, friend, and role model for many.

In debates over the future of artificial intelligence, many experts think of these machine-based systems as coldly logical and objectively rational. But in a new study, Princeton University-based researchers have demonstrated how machines can be reflections of their creators in potentially problematic ways. Common machine-learning programs trained with ordinary human language available online can acquire the cultural biases embedded in the patterns of wording, the researchers reported in the journal Science April 14. These biases range from the morally neutral, such as a preference for flowers over insects, to discriminatory views on race and gender. Identifying and addressing possible biases in machine learning will be critically important as we increasingly turn to computers for processing the natural language humans use to communicate, as in online text searches, image categorization and automated translations.