SANTA CLARA, Jan. 28, 2020 – ServiceNow (NYSE: NOW), the company making work, work better for people, today announced it has signed an agreement to acquire Passage AI, a Mountain View, Calif.–based conversational AI platform company. The transaction will advance ServiceNow's deep learning AI capabilities and will accelerate its vision of supporting all major languages across the company's Now Platform and products, including ServiceNow Virtual Agent, Service Portal, Workspaces and emerging interfaces. "Work flows more smoothly when people can get things done in their native language," said Debu Chatterjee, senior director of AI Engineering at ServiceNow. "Building deep learning, conversational AI capabilities into the Now Platform will enable a work request initiated in German or a customer inquiry initiated in Japanese to be solved by Virtual Agent. Passage AI's technology will enable us to accelerate our vision of empowering great employee and customer experiences by delivering great workflow experiences. ServiceNow believes in making work flow more smoothly across the enterprise, in all major languages."

If you want a machine to learn to do something intelligent you either have to program it or teach it to learn. For decades, engineers have been programming machines to perform all sorts of tasks -- from software that runs on your personal computer and smartphone to guidance control for space missions. But although computers are generally much faster and more precise than the human brain at sequential tasks, such as adding numbers or calculating chess moves, such programs are very limited in their scope. Something as trivial as identifying a bicycle among a crowded pedestrian street or picking up a hot cup of coffee from a desk and gently moving it to the mouth can send a computer into convulsions, nevermind conceptualizing or abstraction (such as designing a computer itself). The gist is that humans were never programmed (not like a digital computer, at least) -- humans have become intelligent through learning.

In this tutorial, we will combine techniques in both computer vision and natural language processing to form a complete image description approach. This will be responsible for constructing computer-generated natural descriptions of any provided images. The idea is to replace the encoder (RNN layer) in an encoder-decoder architecture with a deep convolutional neural network (CNN) trained to classify objects in images. Normally, the CNN's last layer is the softmax layer, which assigns the probability that each object might be in the image. But if we remove that softmax layer from CNN, we can feed the CNN's rich encoding of the image into the decoder (language generation RNN) designed to produce phrases.

There will be three rooms. The event is a semi-organised unconference. The nature of the sessions is determined by those attending the unconference, however, we're interested broadly in the fields of machine learning, artificial intelligence, deep learning, and related fields, but with a particular focus on:

In recent years, significant attention has been devoted towards integrating deep learning technologies in the healthcare domain. However, to safely and practically deploy deep learning models for home health monitoring, two significant challenges must be addressed: the models should be (1) robust against noise; and (2) compact and energy-efficient. We propose REST, a new method that simultaneously tackles both issues via 1) adversarial training and controlling the Lipschitz constant of the neural network through spectral regularization while 2) enabling neural network compression through sparsity regularization. We demonstrate that REST produces highly-robust and efficient models that substantially outperform the original full-sized models in the presence of noise. For the sleep staging task over single-channel electroencephalogram (EEG), the REST model achieves a macro-F1 score of 0.67 vs. 0.39 achieved by a state-of-the-art model in the presence of Gaussian noise while obtaining 19x parameter reduction and 15x MFLOPS reduction on two large, real-world EEG datasets. By deploying these models to an Android application on a smartphone, we quantitatively observe that REST allows models to achieve up to 17x energy reduction and 9x faster inference. We open-source the code repository with this paper: https://github.com/duggalrahul/REST.

Deep neural networks (DNNs) have been employed for designing wireless systems in many aspects, say transceiver design, resource optimization, and information prediction. Existing works either use the fully-connected DNN or the DNNs with particular architectures developed in other domains. While generating labels for supervised learning and gathering training samples are time-consuming or cost-prohibitive, how to develop DNNs with wireless priors for reducing training complexity remains open. In this paper, we show that two kinds of permutation invariant properties widely existed in wireless tasks can be harnessed to reduce the number of model parameters and hence the sample and computational complexity for training. We find special architecture of DNNs whose input-output relationships satisfy the properties, called permutation invariant DNN (PINN), and augment the data with the properties. By learning the impact of the scale of a wireless system, the size of the constructed PINNs can flexibly adapt to the input data dimension. We take predictive resource allocation and interference coordination as examples to show how the PINNs can be employed for learning the optimal policy with unsupervised and supervised learning. Simulations results demonstrate a dramatic gain of the proposed PINNs in terms of reducing training complexity.

Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample. Adversarial attacks that render DNNs vulnerable in real life represent a serious threat, given the consequences of improperly functioning autonomous vehicles, malware filters, or biometric authentication systems. In this paper, we apply Fast Gradient Sign Method to introduce perturbations to a facial image dataset and then test the output on a different classifier that we trained ourselves, to analyze transferability of this method. Next, we craft a variety of different attack algorithms on a facial image dataset, with the intention of developing untargeted black-box approaches assuming minimal adversarial knowledge, to further assess the robustness of DNNs in the facial recognition realm. We explore modifying single optimal pixels by a large amount, or modifying all pixels by a smaller amount, or combining these two attack approaches. While our single-pixel attacks achieved about a 15% average decrease in classifier confidence level for the actual class, the all-pixel attacks were more successful and achieved up to an 84% average decrease in confidence, along with an 81.6% misclassification rate, in the case of the attack that we tested with the highest levels of perturbation. Even with these high levels of perturbation, the face images remained fairly clearly identifiable to a human. We hope our research may help to advance the study of adversarial attacks on DNNs and defensive mechanisms to counteract them, particularly in the facial recognition domain.

We apply generative adversarial network (GAN) technology to build an event generator that simulates particle production in electron-proton scattering that is free of theoretical assumptions about underlying particle dynamics. The difficulty of efficiently training a GAN event simulator lies in learning the complicated patterns of the distributions of the particles physical properties. We develop a GAN that selects a set of transformed features from particle momenta that can be generated easily by the generator, and uses these to produce a set of augmented features that improve the sensitivity of the discriminator. The new Feature-Augmented and Transformed GAN (FA T -GAN) is able to faithfully reproduce the distribution of final state electron momenta in inclusive electron scattering, without the need for input derived from domain-based theoretical assumptions. The developed technology can play a significant role in boosting the science of the Jefferson Lab 12 GeV program and the future Electron-Ion Collider.

Understanding intrinsic patterns and predicting spatiotemporal characteristics of cities require a comprehensive representation of urban neighborhoods. Existing works relied on either inter- or intra-region connectivities to generate neighborhood representations but failed to fully utilize the informative yet heterogeneous data within neighborhoods. In this work, we propose Urban2Vec, an unsupervised multi-modal framework which incorporates both street view imagery and point-of-interest (POI) data to learn neighborhood embeddings. Specifically, we use a convolutional neural network to extract visual features from street view images while preserving geospatial similarity. Furthermore, we model each POI as a bag-of-words containing its category, rating, and review information. Analog to document embedding in natural language processing, we establish the semantic similarity between neighborhood ("document") and the words from its surrounding POIs in the vector space. By jointly encoding visual, textual, and geospatial information into the neighborhood representation, Urban2Vec can achieve performances better than baseline models and comparable to fully-supervised methods in downstream prediction tasks. Extensive experiments on three U.S. metropolitan areas also demonstrate the model interpretability, generalization capability, and its value in neighborhood similarity analysis.

ABSTRACT Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even dialects of the same language. One aspect that has been mostly neglected, however, is discrimination of languages for multilingual speakers, despite being a primary target audience of many systems that utilize LID technologies. As we show in this work, LID systems can have a high average accuracy for most combinations of languages while greatly underper-forming for others when accented speech is present. We address this by using coarser-grained targets for the acoustic LID model and integrating its outputs with interaction context signals in a context-aware model to tailor the system to each user. This combined system achieves an average 97% accuracy across all language combinations while improving worst-case accuracy by over 60% relative to our baseline.