Diffusion-based classifiers such as those relying on the Personalized PageRank and the Heat kernel, enjoy remarkable classification accuracy at modest computational requirements. Their performance however is affected by the extent to which the chosen diffusion captures a typically unknown label propagation mechanism, that can be specific to the underlying graph, and potentially different for each class. The present work introduces a disciplined, data-efficient approach to learning class-specific diffusion functions adapted to the underlying network topology. The novel learning approach leverages the notion of "landing probabilities" of class-specific random walks, which can be computed efficiently, thereby ensuring scalability to large graphs. This is supported by rigorous analysis of the properties of the model as well as the proposed algorithms. Furthermore, a robust version of the classifier facilitates learning even in noisy environments. Classification tests on real networks demonstrate that adapting the diffusion function to the given graph and observed labels, significantly improves the performance over fixed diffusions; reaching -- and many times surpassing -- the classification accuracy of computationally heavier state-of-the-art competing methods, that rely on node embeddings and deep neural networks.

Identifying the distribution of users' transportation modes is an essential part of travel demand analysis and transportation planning. With the advent of ubiquitous GPS-enabled devices (e.g., a smartphone), a cost-effective approach for inferring commuters' mobility mode(s) is to leverage their GPS trajectories. A majority of studies have proposed mode inference models based on hand-crafted features and traditional machine learning algorithms. However, manual features engender some major drawbacks including vulnerability to traffic and environmental conditions as well as possessing human's bias in creating efficient features. One way to overcome these issues is by utilizing Convolutional Neural Network (CNN) schemes that are capable of automatically driving high-level features from the raw input. Accordingly, in this paper, we take advantage of CNN architectures so as to predict travel modes based on only raw GPS trajectories, where the modes are labeled as walk, bike, bus, driving, and train. Our key contribution is designing the layout of the CNN's input layer in such a way that not only is adaptable with the CNN schemes but represents fundamental motion characteristics of a moving object including speed, acceleration, jerk, and bearing rate. Furthermore, we ameliorate the quality of GPS logs through several data preprocessing steps. Using the clean input layer, a variety of CNN configurations are evaluated to achieve the best CNN architecture. The highest accuracy of 84.8% has been achieved through the ensemble of the best CNN configuration. In this research, we contrast our methodology with traditional machine learning algorithms as well as the seminal and most related studies to demonstrate the superiority of our framework.

Lets talk about the coolest tech there is: Artificial Intelligence. It may be the stuff of futuristic movies, but AI is here and now. We might not quite be at the'I, Robot' stage just yet, but we're getting there with self-driving cars and smart homes. This is all assuming we're not already in The Matrix of course. The idea of machines learning is an immensely exciting concept, and increasingly it's driving the way the world around us operates.

A major transformation is happening now as technological advancements and escalating volumes of diverse data drive change across all industries. Cutting-edge innovations are fueling digital transformation on a global scale, and organizations are leveraging faster, more powerful machines to operate more intelligently and effectively than ever. Recently, Hewlett Packard Enterprise (HPE) has announced the new HPE Apollo 6500 Gen10 server, a groundbreaking platform designed to tackle the most compute-intensive high performance computing (HPC) and deep learning workloads. Deep learning – an exciting development in artificial intelligence (AI) – enables machines to solve highly complex problems quickly by autonomously analyzing and learning from enormous datasets. Backed by the robust HPC capabilities of the HPE Apollo 6500 Gen10, organizations can uncover deep insight at lightning speeds and turbocharge data analytics to optimize decision-making, utilize predictive analytics, enhance business processes, resolve hidden problems in data, and much more.

Entity extraction from text is a major Natural Language Processing (NLP) task. As the recent advancement in the deep learning(DL) enable us to use them for NLP tasks and producing huge differences in accuracy compared to traditional methods. I have attempted to extract the information from article using both deep learning and traditional methods. Result was amazing as DL method got accuracy of 85% over 65% from legacy methods. The aim of the project is to tag each words of the articles into 4 categories: organisation, person, miscellaneous, and other.

The receptive field is perhaps one of the most important concepts in Convolutional Neural Networks (CNNs) that deserves more attention from the literature. All of the state-of-the-art object recognition methods design their model architectures around this idea. However, to my best knowledge, currently there is no complete guide on how to calculate and visualize the receptive field information of a CNN. This post fills in the gap by introducing a new way to visualize feature maps in a CNN that exposes the receptive field information, accompanied by a complete receptive field calculation that can be used for any CNN architecture. I've also implemented a simple program to demonstrate the calculation so that anyone can start computing the receptive field and gain better knowledge about the CNN architecture that they are working with.

Billionaire hedge fund investor Steven Cohen's venture capital group announced this week it had co-led a $15 million investment round in a Silicon Valley startup that is developing artificial-intelligence software for driver assistance and autonomous driving. Mountain View, Calif.-based DeepScale supports automated driving with "deep neural network" software that uses low-power, automotive-grade chips to detect vehicles, pedestrians and other "objects of significance." By doing so, DeepScale officials said they aim to bring driver-assistance and autonomous driving to mass-produced vehicles at all price points. "We've been following (DeepScale co-founder and CEO) Forrest Iandola's research on efficient deep learning for a number of years," Sri Chandrasekar, a Point72 director, said in a statement. "Forrest's inventions … have already been a game-changer for putting deep learning onto smartphones. When we heard that Forrest had started a company to put small DNNs into mass-produced cars, we jumped at the opportunity to get involved."

Using lidar and a healthy dose of AI, a new robot can check that building projects are going to plan. How it works: Once a construction site shuts down for the night, a small robot deployed by startup Doxel can get to work. Using lidar, it scans the site and uploads data to the cloud. There, deep-learning algorithms flag anything that deviates from building plans so that a manager can fix it the day after. Why it matters: If errors aren't noticed immediately on a work site, they can create compounding issues that take time and money to put right down the line.

As radiology is inherently a data-driven specialty, it is especially conducive to utilizing data processing techniques. One such technique, deep learning (DL), has become a remarkably powerful tool for image processing in recent years. In this work, the Association of University Radiologists Radiology Research Alliance Task Force on Deep Learning provides an overview of DL for the radiologist. This article aims to present an overview of DL in a manner that is understandable to radiologists; to examine past, present, and future applications; as well as to evaluate how radiologists may benefit from this remarkable new tool. We describe several areas within radiology in which DL techniques are having the most significant impact: lesion or disease detection, classification, quantification, and segmentation.

Perception system design is a very critical step in the development of an autonomous vehicle (AV). To obtain human level perception, autonomous vehicles primarily use sensor technologies such as LiDARs, RADARs, and Cameras. Self-driving vehicles also need to be equipped with state-of-the-art AV perception technology. DeepScale is a leader in efficient deep learning perception software for use in mass-produced automated vehicles. Today, the company announced it has secured a $15 million Series A funding investment led by Point72 and next47.