Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid. Identifying insights helps analysts understand the collaboration of various parts of the grid so that preventive and correct operations can be taken to avoid potential accidents. Existing solutions for identifying insights in PGPMs are performed manually, which may be laborious and expertise-dependent. In this paper, we propose an interactive insight identification and annotation framework by leveraging an enhanced variational autoencoder (VAE). In particular, a new architecture, DenseU-Hierarchical VAE (DUHiV), is designed to learn representations from large-sized PGPMs, which achieves a significantly tighter evidence lower bound (ELBO) than existing Hierarchical VAEs with a Multilayer Perceptron architecture. Our approach supports modulating the derived representations in an interactive visual interface, discover potential insights and create multi-label annotations. Evaluations using real-world PGPMs datasets show that our framework outperforms the baseline models in identifying and annotating insights.

Modeling and forecasting forward citations to a patent is a central task for the discovery of emerging technologies and for measuring the pulse of inventive progress. Conventional methods for forecasting these forward citations cast the problem as analysis of temporal point processes which rely on the conditional intensity of previously received citations. Recent approaches model the conditional intensity as a chain of recurrent neural networks to capture memory dependency in hopes of reducing the restrictions of the parametric form of the intensity function. For the problem of patent citations, we observe that forecasting a patent's chain of citations benefits from not only the patent's history itself but also from the historical citations of assignees and inventors associated with that patent. In this paper, we propose a sequence-to-sequence model which employs an attention-of-attention mechanism to capture the dependencies of these multiple time sequences. Furthermore, the proposed model is able to forecast both the timestamp and the category of a patent's next citation. Extensive experiments on a large patent citation dataset collected from USPTO demonstrate that the proposed model outperforms state-of-the-art models at forward citation forecasting.

Point cloud data from 3D LiDAR sensors are one of the most crucial sensor modalities for versatile safety-critical applications such as self-driving vehicles. Since the annotations of point cloud data is an expensive and time-consuming process, therefore recently the utilisation of simulated environments and 3D LiDAR sensors for this task started to get some popularity. With simulated sensors and environments, the process for obtaining an annotated synthetic point cloud data became much easier. However, the generated synthetic point cloud data are still missing the artefacts usually exist in point cloud data from real 3D LiDAR sensors. As a result, the performance of the trained models on this data for perception tasks when tested on real point cloud data is degraded due to the domain shift between simulated and real environments. Thus, in this work, we are proposing a domain adaptation framework for bridging this gap between synthetic and real point cloud data. Our proposed framework is based on the deep cycle-consistent generative adversarial networks (CycleGAN) architecture. We have evaluated the performance of our proposed framework on the task of vehicle detection from a bird's eye view (BEV) point cloud images coming from real 3D LiDAR sensors. The framework has shown competitive results with an improvement of more than 7% in average precision score over other baseline approaches when tested on real BEV point cloud images.

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error. However, compressive networks are desired in many real world applications and direct training of small networks may be trapped in local optima. In this paper, instead of pruning or distilling an over-parameterized model to compressive ones, we propose a parsimonious learning approach based on differential inclusions of inverse scale spaces, that generates a family of models from simple to complex ones with a better efficiency and interpretability than stochastic gradient descent in exploring the model space. It enjoys a simple discretization, the Split Linearized Bregman Iterations, with provable global convergence that from any initializations, algorithmic iterations converge to a critical point of empirical risks. One may exploit the proposed method to boost the complexity of neural networks progressively. Numerical experiments with MNIST, Cifar-10/100, and ImageNet are conducted to show the method is promising in training large scale models with a favorite interpretability.

Characterizing temporal dependence patterns is a critical step in understanding the statistical properties of sequential data. Long Range Dependence (LRD) --- referring to long-range correlations decaying as a power law rather than exponentially w.r.t. distance --- demands a different set of tools for modeling the underlying dynamics of the sequential data. While it has been widely conjectured that LRD is present in language modeling and sequential recommendation, the amount of LRD in the corresponding sequential datasets has not yet been quantified in a scalable and model-independent manner. We propose a principled estimation procedure of LRD in sequential datasets based on established LRD theory for real-valued time series and apply it to sequences of symbols with million-item-scale dictionaries. In our measurements, the procedure estimates reliably the LRD in the behavior of users as they write Wikipedia articles and as they interact with YouTube. We further show that measuring LRD better informs modeling decisions in particular for RNNs whose ability to capture LRD is still an active area of research. The quantitative measure informs new Evolutive Recurrent Neural Networks (EvolutiveRNNs) designs, leading to state-of-the-art results on language understanding and sequential recommendation tasks at a fraction of the computational cost.

Phishing is the simplest form of cybercrime with the objective of baiting people into giving away delicate information such as individually recognizable data, banking and credit card details, or even credentials and passwords. This type of simple yet most effective cyber-attack is usually launched through emails, phone calls, or instant messages. The credential or private data stolen are then used to get access to critical records of the victims and can result in extensive fraud and monetary loss. Hence, sending malicious messages to victims is a stepping stone of the phishing procedure. A phisher usually setups a deceptive website, where the victims are conned into entering credentials and sensitive information. It is therefore important to detect these types of malicious websites before causing any harmful damages to victims. Inspired by the evolving nature of the phishing websites, this paper introduces a novel approach based on deep reinforcement learning to model and detect malicious URLs. The proposed model is capable of adapting to the dynamic behavior of the phishing websites and thus learn the features associated with phishing website detection. I. INTRODUCTION Phishing is a form of cyber attack typically performed by sending false correspondences that seem to be originated from a legitimate source.

Summary: If you are guiding your company's digital journey, to what extent should you be advising them to adopt deep learning AI methods versus traditional and mature machine learning techniques. By now everyone is at least familiar with using AI/ML as a required cornerstone of company strategy. Frequently this is referred to as'digitization' or the'digital journey'. There's plenty of data showing that early adopters who have gone all-in on this approach are already pulling ahead of competitors both in share and bottom line results. There's also mounting evidence that even though most companies are now aware of this need, either their planning or their execution has been half-hearted.

Google AI researchers working with Northwestern Medicine created an AI model capable of detecting lung cancer from screening tests better than human radiologists with an average of eight years experience. When analyzing a single CT scan, the model detected cancer 5% more often on average than a group of six human experts and was 11% more likely to reduce false positives. Humans and AI achieved similar results when radiologists were able to view prior CT scans. When it came to predicting the risk of cancer two years after a screening, the model was able to find cancer 9.5% more often compared to estimated radiologist performance laid out in the National Lung Screening Test (NLST) study. Detailed in research published today in Nature Medicine, the end-to-end deep learning model was used to predict whether a patient has lung cancer, generating a patient lung cancer malignancy risk score and identifying the location of the malignant tissue in the lungs.

CHICAGO --- Deep learning - a form of artificial intelligence - was able to detect malignant lung nodules on low-dose chest computed tomography (LDCT) scans with a performance meeting or exceeding that of expert radiologists, reports a new study from Google and Northwestern Medicine. This deep-learning system provides an automated image evaluation system to enhance the accuracy of early lung cancer diagnosis that could lead to earlier treatment. The deep-learning system was compared against radiologists on LDCTs for patients, some of whom had biopsy confirmed cancer within a year. In most comparisons, the model performed at or better than radiologists. Deep learning is a technique that teaches computers to learn by example.

CHICAGO --- Deep learning - a form of artificial intelligence - was able to detect malignant lung nodules on low-dose chest computed tomography (LDCT) scans with a performance meeting or exceeding that of expert radiologists, reports a new study from Google and Northwestern Medicine. This deep-learning system provides an automated image evaluation system to enhance the accuracy of early lung cancer diagnosis that could lead to earlier treatment. The deep-learning system was compared against radiologists on LDCTs for patients, some of whom had biopsy confirmed cancer within a year. In most comparisons, the model performed at or better than radiologists. Deep learning is a technique that teaches computers to learn by example.