Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL. First, we classify different MTL algorithms into several categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach, and decomposition approach, and then discuss the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, batch MTL models are difficult to handle this situation and online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing are reviewed to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works. Finally, we present theoretical analyses and discuss several future directions for MTL.

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of prediction accuracy between the quantized model and the full-precision model. To address this gap, we propose to jointly train a quantized, bit-operation-compatible DNN and its associated quantizers, as opposed to using fixed, handcrafted quantization schemes such as uniform or logarithmic quantization. Our method for learning the quantizers applies to both network weights and activations with arbitrary-bit precision, and our quantizers are easy to train. The comprehensive experiments on CIFAR-10 and ImageNet datasets show that our method works consistently well for various network structures such as AlexNet, VGG-Net, GoogLeNet, ResNet, and DenseNet, surpassing previous quantization methods in terms of accuracy by an appreciable margin.

SUNNYVALE, Calif., May 11, 2018 –Socionext Inc., a leading provider of SoC-based solutions, has developed a new Neural Network Accelerator (NNA) engine, optimized for AI processing on edge computing devices. The compact, low power engine has been designed specifically for deep learning inference processing. When implemented, it can achieve 100x performance boost compared with conventional processors for computer vision processing such as image recognition. Socionext will start delivering the Software Development Kit for the FPGA implementation of the NNA in the third quarter of 2018. The company is also planning to develop its SoC products with the NNA.

AIs that can work out how to hack self driving cars and other vehicles to turn them into killers are coming - and sooner than many people think, a leading expert has warned. 'Such attacks, which seem like science fiction today, might become reality in the next few years,' Guy Caspi, CEO of cybersecurity start-up Deep Instinct, told CNBC's podcast'Beyond the Valley.' It raises fears that self driving cars and other technologies could be hacked, turning them into makeshift battle weapons. Security expert Guy Caspi claims the technology needed for killer vehicles already exists in self driving cars from firms like Alphabet's Waymo. Caspi says much of the technology needed for killer vehicles already exists.

Don't miss this opportunity to hear from some of the top leaders in the semiconductor industry as they discuss how AI, Machine Learning and Deep Learning are impacting various technology segments and market verticals. Following will be an interactive panel discussion on AI.

Computer-aided review of X-rays can help diagnose people with lung illnesses such as tuberculosis and pneumonia. Such review, augmented by deep learning, can help lead to earlier detection and treatment of these conditions, especially in remote areas where specialists are typically in short supply, according to new research. About one third of people in the world may be infected with tuberculosis. In 2016, there were more than 10 million cases of active tuberculosis, resulting in 1.3 million deaths. It's the No. 1 cause of death for an infectious disease, and more than 95 percent of these deaths occurred in developing countries.

Image classification and object detection in images are hot topics these days, thanks to a combination of improvements in algorithms, datasets, frameworks, and hardware. These improvements democratized the technology and gave us the ingredients for creating our own solution for image classification. The state-of-the-art technologies for image classification and object detection are based on deep learning (DL). DL is a subarea of machine learning (ML) that is focused on algorithms for handling neural networks (NN) with many layers, or deep neural networks. ML, in turn, is a subarea of artificial intelligence (AI), a computer-science discipline.

On today's show we talk to the founder of ETFmg, Sam Masucci. Sam's company is responsible for bringing the first Artificial Intelligence ETF onto the market. The name of the ticker is AIEQ, and since inception in OCT 2017, the fund has outperformed the S&P 500 by nearly twice the yield (as of July 2018). During our discussion with Sam, we ask him about the deep learning methodology and how the programmers integrated IBM Watson technology into the logic. Additionally, we talk to Sam about another artificial intelligence ETF called BIKR, which was designed and launched by the legendary investor, Jim Rogers.

At DKdL (Die Krieger des Lichts, part of the fischerAppelt group) we have decided to take a novel and holistic approach to developing intelligent data-driven concepts and products. We call this approach "human centered AI", where AI stands for artificial intelligence. Our approach integrates the research & development (R&D) needed to develop AI systems into a human centered design process. In simple words, we understand that the intelligent products (that is, products that use AI at their core) we develop are designed to be used by humans in a way that adds value to their daily experiences. Therefore, we start by understanding the people who are going to use the product and the needs it is intended to meet. We then keep those needs at the focus of our considerations throughout the entire development process and the design iterations.

Vestorly, an AI-powered content marketing platform, announced the launch of new AI-guided content curation features to emulate marketers more effectively over time and increase engagement rates with consumers. "It operates like a marketing assistant, continually taking into account the interests of the intended audience, but also personal traits and objectives." "Vestorly can now find patterns among abstract concepts and attempt to represent a given marketer in its content curation," said Vestorly CEO Justin Wisz. "It operates like a marketing assistant, continually taking into account the interests of the intended audience, but also personal traits and objectives." Through an interactive interface for users of all types, Vestorly collects volunteered information from marketers about themselves and their audience.