From a practical point of view, the following experiments were carried out in Keras and run on an amazon GPU instance. I've been amazed by the power of neural network models. Intuitively, I don't have an explanation of how they are so powerful at learning representations of text. It makes some sense that a model with so many parameters could reproduce the results here. What's impressive is that they can be trained by simple stochastic gradient decent.

When it comes to enterprise customer care, machine learning enables virtual assistant solutions to automate tasks that used to require a live agent: password resets, address and complex information collection, even sales support. Integrating machine learning into enterprise customer care opens doors to more flexible automated solutions. It also frees up live agents to focus on handling complex or revenue-generating tasks. With the growing challenges and volume of customer interactions that most companies must handle, that flexibility, efficiency, and accuracy is exactly what's needed. With a little help and vetting from the IT department, the contact center can take enterprise customer care to the next level. Of course, success comes with a cost.

Researchers at the University of Leuven in Belgium said a study they conducted showed artificial intelligence could help interpret, and thereby improve, lung function tests used to diagnose long-term lung disease. Results of the study were presented Monday at the European Respiratory Society's International Congress. As part of the study, the researchers used data from 968 people who were undergoing complete lung function testing for the first time. Using a concept called "machine learning", they developed an algorithm that takes into account routine lung function parameters and clinical variables of smoking history, body mass index, and age to make a suggestion for the most likely diagnosis. "We have demonstrated that artificial intelligence can provide us with a more accurate diagnosis in this new study," Wim Janssens, senior author of the study, said.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

Fingerprints can be stolen, iris scans spoofed, and facial recognition software fooled. It has become increasingly challenging to unassailably authenticate a person's identity, so academic teams have turned to brain waves as the next step in biometric identification. Many of these efforts seek to outdo one another, boasting how accurately and accessibly they can verify a person's identity using electroencephalograph (EEG) data. In April, for example, a team in New York achieved 100 percent accuracy at identifying individuals using a skullcap with 30 electrodes. Last week, we reported on a simple set of earbud sensors that worked with 80 percent accuracy.

In a recent paper, "Why does deep and cheap learning work so well?", Lin and Tegmark claim to show that the mapping between deep belief networks and the variational renormalization group derived in [arXiv:1410.3831] is invalid, and present a "counterexample" that claims to show that this mapping does not hold. In this comment, we show that these claims are incorrect and stem from a misunderstanding of the variational RG procedure proposed by Kadanoff. We also explain why the "counterexample" of Lin and Tegmark is compatible with the mapping proposed in [arXiv:1410.3831].

In an era of ubiquitous large-scale streaming data, the availability of data far exceeds the capacity of expert human analysts. In many settings, such data is either discarded or stored unprocessed in datacenters. This paper proposes a method of online data thinning, in which large-scale streaming datasets are winnowed to preserve unique, anomalous, or salient elements for timely expert analysis. At the heart of this proposed approach is an online anomaly detection method based on dynamic, low-rank Gaussian mixture models. Specifically, the high-dimensional covariances matrices associated with the Gaussian components are associated with low-rank models. According to this model, most observations lie near a union of subspaces. The low-rank modeling mitigates the curse of dimensionality associated with anomaly detection for high-dimensional data, and recent advances in subspace clustering and subspace tracking allow the proposed method to adapt to dynamic environments. Furthermore, the proposed method allows subsampling, is robust to missing data, and uses a mini-batch online optimization approach. The resulting algorithms are scalable, efficient, and are capable of operating in real time. Experiments on wide-area motion imagery and e-mail databases illustrate the efficacy of the proposed approach.

The process of dynamic state estimation (filtering) based on point process observations is in general intractable. Numerical sampling techniques are often practically useful, but lead to limited conceptual insight about optimal encoding/decoding strategies, which are of significant relevance to Computational Neuroscience. We develop an analytically tractable Bayesian approximation to optimal filtering based on point process observations, which allows us to introduce distributional assumptions about sensor properties, that greatly facilitate the analysis of optimal encoding in situations deviating from common assumptions of uniform coding. Numerical comparison with particle filtering demonstrate the quality of the approximation. The analytic framework leads to insights which are difficult to obtain from numerical algorithms, and is consistent with biological observations about the distribution of sensory cells' tuning curve centers.

Process mining is a research field focused on the analysis of event data with the aim of extracting insights in processes. Applying process mining techniques on data from smart home environments has the potential to provide valuable insights in (un)healthy habits and to contribute to ambient assisted living solutions. Finding the right event labels to enable application of process mining techniques is however far from trivial, as simply using the triggering sensor as the label for sensor events results in uninformative models that allow for too much behavior (overgeneralizing). Refinements of sensor level event labels suggested by domain experts have shown to enable discovery of more precise and insightful process models. However, there exist no automated approach to generate refinements of event labels in the context of process mining. In this paper we propose a framework for automated generation of label refinements based on the time attribute of events. We show on a case study with real life smart home event data that behaviorally more specific, and therefore more insightful, process models can be found by using automatically generated refined labels in process discovery.

Several recent deep neural networks experiments leverage the generalist-specialist paradigm for classification. However, no formal study compared the performance of different clustering algorithms for class assignment. In this paper we perform such a study, suggest slight modifications to the clustering procedures, and propose a novel algorithm designed to optimize the performance of of the specialist-generalist classification system. Our experiments on the CIFAR-10 and CIFAR-100 datasets allow us to investigate situations for varying number of classes on similar data. We find that our \emph{greedy pairs} clustering algorithm consistently outperforms other alternatives, while the choice of the confusion matrix has little impact on the final performance.