Convolutional neural networks (CNNs) are inherently subject to invariable filters that can only aggregate local inputs with the same topological structures. It causes that CNNs are allowed to manage data with Euclidean or grid-like structures (e.g., images), not ones with non-Euclidean or graph structures (e.g., traffic networks). To broaden the reach of CNNs, we develop structure-aware convolution to eliminate the invariance, yielding a unified mechanism of dealing with both Euclidean and non-Euclidean structured data. Technically, filters in the structure-aware convolution are generalized to univariate functions, which are capable of aggregating local inputs with diverse topological structures. Since infinite parameters are required to determine a univariate function, we parameterize these filters with numbered learnable parameters in the context of the function approximation theory. By replacing the classical convolution in CNNs with the structure-aware convolution, Structure-Aware Convolutional Neural Networks (SACNNs) are readily established. Extensive experiments on eleven datasets strongly evidence that SACNNs outperform current models on various machine learning tasks, including image classification and clustering, text categorization, skeleton-based action recognition, molecular activity detection, and taxi flow prediction.

As computing and storage went cheaper, Big Data came up. The words being used as buzz shifted to the machine and deep machine learning when early adopters had a single source of truth. Now, learning from this single source of data took the main-stage. This wave created a lot of new jobs and the profile of Data Analyst was born with most of them working for US companies who were investing in this. It graduated to Big Data Analyst and then Data Scientist and Machine Learning Engineer and the profiles evolving and becoming more and more specific in nature.

There's no fighting it, AI is the future of technology. Computing systems with advanced learning algorithms are revolutionizing new industries even as we speak. But let's not be naïve. AI requires a robust support system to train and perform properly. Neuromation is a distributed synthetic data platform for deep learning applications.

There is an avalanche of research publishing in the field of machine learning, something Google engineer Cliff Young has likened to a "Moore's Law" of AI publishing, with the number of academic papers on the topic that are posted on the arXiv pre-print server doubling every 18 months. All that creates problems for peer reviewing the work, what with experienced AI researchers too few to possibly read each and every paper carefully. What if machines could do some of the heavy lifting? Should academics trust their own acceptance or rejection to an AI? Also: Google says'exponential' growth of AI is changing nature of compute That's the intriguing question raised by a report posted Thursday, on arXiv, by a machine learning researcher at Virginia Tech, Jia-Bin Huang, titled "Deep Paper Gestalt." Huang used a convolutional neural network, or CNN, the stock tool of machine learning for image recognition, to sift through over 5,000 papers submitted to academic conferences dating back to 2013. Huang writes that purely on the basis of the look of a paper -- its mix of text and images -- his neural net can select a "good" paper, one deserving of inclusion in a conference, with 92% accuracy.

Artificial intelligence (AI) can generate eerily realistic faces, but what about tribal artwork? That's the question Victor Dibia, a human-computer interaction researcher and Carnegie Mellon graduate, sought to answer with an AI system trained on a dataset of African masks. As Dibia explains in a blog post, the work was inspired by a trip to the 2018 Deep Learning Indaba, an annual machine learning conference held at Stellenbosch University, South Africa, in September. Attendees were provided access to second-generation Tensor Processing Units (TPUs) -- Google-designed chips purpose-built for fast training or inference of AI models -- which Dibia used for training. He tapped Google's TensorFlow machine learning framework to get a generative adversarial network (GAN) -- a two-part neural network consisting of generators that produce samples and discriminators that attempt to distinguish between the generated samples and real-world samples -- up and running on the TPUs.

In this article, we'll take a moment to look at some of the interesting things that transpired in 2018 in the machine learning world. We'll look at some of the top open source projects as ranked by Mybridge, major developments in machine learning frameworks, and some of the things to look forward to in 2019. Let's look at some of the top open source projects from the previous year BERT stands for Bidirectional Encoder Representations from Transformers. BERT is a new method of solving natural language processing problems and obtains state of the art results. It's based on TensorFlow and allows developers to solve problems using pre-trained models.

Choose the Deep Learning bundle that's right for you!

Indian AI-powered software firm Staqu has revealed the launch of TRINETRA, an AI application for the Uttar Pradesh Police Department. The application digitizes and search records using AI and carries records of criminals, assisting police forces at ground zero with real-time information retrieval during investigations, regular checks, verifications, and at police checkpoints. The firm said the app is powered by Staqu's expertise in facial recognition, visual search, machine learning, and deep learning, works well with low-resolution images and videos, and offers better accuracy than any other criminal recognition system. "With AI-powered Gang identification Technology, TRIENETRA not only identifies a criminal but also their associates active in different districts and part of the states."

Leishmaniasis is considered a neglected disease that causes thousands of deaths annually in some tropical and subtropical countries. There are various techniques to diagnose leishmaniasis of which manual microscopy is considered to be the gold standard. There is a need for the development of automatic techniques that are able to detect parasites in a robust and unsupervised manner. In this paper we present a procedure for automatizing the detection process based on a deep learning approach. We train a U-net model that successfully segments leismania parasites and classifies them into promastigotes, amastigotes and adhered parasites.

Preparation of high-quality datasets for the urban scene understanding is a labor-intensive task, especially, for datasets designed for the autonomous driving applications. The application of the coarse ground truth (GT) annotations of these datasets without detriment to the accuracy of semantic image segmentation (by the mean intersection over union - mIoU) could simplify and speedup the dataset preparation and model fine tuning before its practical application. Here the results of the comparative analysis for semantic segmentation accuracy obtained by PSPNet deep learning architecture are presented for fine and coarse annotated images from Cityscapes dataset. Two scenarios were investigated: scenario 1 - the fine GT images for training and prediction, and scenario 2 - the fine GT images for training and the coarse GT images for prediction. The obtained results demonstrated that for the most important classes the mean accuracy values of semantic image segmentation for coarse GT annotations are higher than for the fine GT ones, and the standard deviation values are vice versa. It means that for some applications some unimportant classes can be excluded and the model can be tuned further for some classes and specific regions on the coarse GT dataset without loss of the accuracy even. Moreover, this opens the perspectives to use deep neural networks for the preparation of such coarse GT datasets.