Imagine a highly banal situation: a busy junction in a major city, vehicles of every color and description, some moving and others waiting for the lights to change. This situation may be boring to death, but fast, powerful computers can view it differently. Once they are "taught" to pick up and distinguish between the most minute details within the larger picture (machine learning, in the professional jargon), they will be able to identify different car models of various colors and issue warnings of irregular events that are about to happen. For example, a man wearing a heavy overcoat when everyone else is wearing short, light garments, or a person under whose clothes a long-bladed knife is protruding, could generate an alert moments before an attack. It is important to understand that machine learning is only one element of the rapidly developing field known as artificial intelligence.

"All you have to do is look at the attacks that have taken place recently--WannaCry, NotPetya and others--and see how quickly the industry and government is coming out and assigning responsibility to nation states such as North Korea, Russia and Iran," said Dmitri Alperovitch, chief technology officer at CrowdStrike Inc., a cybersecurity company that has investigated a number of state-sponsored hacks. The White House and other countries took roughly six months to blame North Korea and Russia for the WannaCry and NotPetya attacks, respectively, while it took about three years for U.S. authorities to indict a North Korean hacker for the 2014 attack against Sony . Forensic systems are gathering and analyzing vast amounts of data from digital databases and registries to glean clues about an attacker's infrastructure. These clues, which may include obfuscation techniques and domain names used for hacking, can add up to what amounts to a unique footprint, said Chris Bell, chief executive of Diskin Advanced Technologies, a startup that uses machine learning to attribute cyberattacks. Additionally, the increasing amount of data related to cyberattacks--including virus signatures, the time of day the attack took place, IP addresses and domain names--makes it easier for investigators to track organized hacking groups and draw conclusions about them.

In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convolution are popular pooling methods. Since the pooling is a lossy procedure, a motivation of our work is to design a new pooling approach for less lossy in the dimensionality reduction. Inspired by the Fourier spectral pooling(FSP) proposed by Rippel et. al. [1], we present the Hartley transform based spectral pooling method in CNNs. Compared with FSP, the proposed spectral pooling avoids the use of complex arithmetic for frequency representation and reduces the computation. Spectral pooling preserves more structure features for network's discriminability than max and average pooling. We empirically show that Hartley spectral pooling gives rise to the convergence of training CNNs on MNIST and CIFAR-10 datasets.

This paper proposes an accelerated proximal stochastic variance reduced gradient (ASVRG) method, in which we design a simple and effective momentum acceleration trick. Unlike most existing accelerated stochastic variance reduction methods such as Katyusha, ASVRG has only one additional variable and one momentum parameter. Thus, ASVRG is much simpler than those methods, and has much lower per-iteration complexity. We prove that ASVRG achieves the best known oracle complexities for both strongly convex and non-strongly convex objectives. In addition, we extend ASVRG to mini-batch and non-smooth settings. We also empirically verify our theoretical results and show that the performance of ASVRG is comparable with, and sometimes even better than that of the state-of-the-art stochastic methods.

Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of human-computer communications, they suffer from the problem of strongly favoring short generic responses. In this paper, we argue that a good response should smoothly connect both the preceding dialogue history and the following conversations. We strengthen this connection through mutual information maximization. To sidestep the non-differentiability of discrete natural language tokens, we introduce an auxiliary continuous code space and map such code space to a learnable prior distribution for generation purpose. Experiments on two dialogue datasets validate the effectiveness of our model, where the generated responses are closely related to the dialogue context and lead to more interactive conversations.

These are just some of the headline-grabbing technologies that could be part of our lives once fifth-generation, or 5G, mobile networks roll out, telcos say. A pilot network in the one-north district is in the pipeline, announced jointly by Singtel and Ericsson in July. M1 will start South-east Asia field trials, and StarHub plans to switch on 5G base stations, both by year-end. But experts and industry players acknowledge that there may be a long road to 5G coverage in Singapore, not least because the dots that are to be connected aren't all in place yet. While the propounded benefits of 5G include higher data volumes and speeds, some raise eyebrows at holding trials and building infrastructure for a system not yet in place.

Researchers at Ecole Centrale de Lyon have recently devised a new developmental framework inspired by the long-term memory and reasoning mechanisms of humans. This framework, outlined in a paper presented at IEEE ICDL-Epirob in Tokyo and pre-published on arXiv, allows robots to autonomously optimize hyper-parameters tuned from any action and/or vision module, which are treated as a black box. In recent years, researchers have built robots that can complete a variety of tasks. Nonetheless, the environment in which these robots operate is often somewhat constrained. This is because in robotics, most algorithms are crafted and optimized manually by human experts to anticipate the potential challenges that the robot might encounter within a given situation.

Recently at the Delta Summit, the Prime Minister of Malta, Joseph Muscat spoke about the blockchain technology and the need for governments to understand the need for regulation. He also mentioned that Artificial Intelligence and best-in-class regulatory framework were the areas that were next in focus for the Malta government. The Prime Minister stated that the Artificial Intelligence technology can be beneficial to the blockchain industry. "We are sure that with AI we can replicate and improve what we are doing now here with blockchain." Joseph stated that they were moving away from a business model based on "decentralization of data."

With the recent news about Facebook and Cambridge analytica, we are rightly concerned about the power and impact of algorithms to shape political debate and more generally, our lives. The social score model in China shows another way in which AI could influence all aspects of society. Based on these and other views, most policy makers in the West take a negative view of AI and the power of algorithms in society. In this post, I present a different, more optimistic view of the impact of AI on society where AI could be a part of the solution to overcome the problem of Algorithmocracy and filter bubbles. I discussed some of the ideas below Last week, I spoke at the Economist innovation summit in London.

For those keeping count, the world is now entering the Fourth Industrial Revolution. That's the term coined by Klaus Schwab, founder and executive chairman of the World Economic Forum, to describe a time when new technologies blur the physical, digital and biological boundaries of our lives. Every generation confronts the challenges of preparing its kids for an uncertain future. Now, for a world that will be shaped by technologies like artificial intelligence, 3D printing and bioengineering, how should society prepare its current students (and tomorrow's workforce)? The popular response, among some education pundits, policymakers and professionals, has been to increase access to STEM and computer science skills.