Recent works using deep learning to solve the Traveling Salesman Problem (TSP) have focused on learning construction heuristics. Such approaches find TSP solutions of good quality but require additional procedures such as beam search and sampling to improve solutions and achieve state-of-the-art performance. However, few studies have focused on improvement heuristics, where a given solution is improved until reaching a near-optimal one. In this work, we propose to learn a local search heuristic based on 2-opt operators via deep reinforcement learning. We propose a policy gradient algorithm to learn a stochastic policy that selects 2-opt operations given a current solution. Moreover, we introduce a policy neural network that leverages a pointing attention mechanism, which unlike previous works, can be easily extended to more general k-opt moves. Our results show that the learned policies can improve even over random initial solutions and approach near-optimal solutions at a faster rate than previous state-of-the-art deep learning methods.

Many areas of research are characterised by the deluge of large-scale highly-dimensional time-series data. However, using the data available for prediction and decision making is hampered by the current lag in our ability to uncover and quantify true interactions that explain the outcomes.We are interested in areas such as intensive care medicine, which are characterised by i) continuous monitoring of multivariate variables and non-uniform sampling of data streams, ii) the outcomes are generally governed by interactions between a small set of rare events, iii) these interactions are not necessarily definable by specific values (or value ranges) of a given group of variables, but rather, by the deviations of these values from the normal state recorded over time, iv) the need to explain the predictions made by the model. Here, while numerous data mining models have been formulated for outcome prediction, they are unable to explain their predictions. We present a model for uncovering interactions with the highest likelihood of generating the outcomes seen from highly-dimensional time series data. Interactions among variables are represented by a relational graph structure, which relies on qualitative abstractions to overcome non-uniform sampling and to capture the semantics of the interactions corresponding to the changes and deviations from normality of variables of interest over time. Using the assumption that similar templates of small interactions are responsible for the outcomes (as prevalent in the medical domains), we reformulate the discovery task to retrieve the most-likely templates from the data.

Traditional code transformation structures, such as an abstract syntax tree, may have limitations in their ability to extract semantic meaning from code. Others have begun to work on this issue, such as the state-of-the-art Aroma system and its simplified parse tree (SPT). Continuing this research direction, we present a new graphical structure to capture semantics from code using what we refer to as a program-derived semantic graph (PSG). The principle behind the PSG is to provide a single structure that can capture program semantics at many levels of granularity. Thus, the PSG is hierarchical in nature. Moreover, because the PSG may have cycles due to dependencies in semantic layers, it is a graph, not a tree. In this paper, we describe the PSG and its fundamental structural differences to the Aroma's SPT. Although our work in the PSG is in its infancy, our early results indicate it is a promising new research direction to explore to automatically extract program semantics.

We present the Goal Uncertain Stochastic Shortest Path (GUSSP) problem -- a general framework to model path planning and decision making in stochastic environments with goal uncertainty. The framework extends the stochastic shortest path (SSP) model to dynamic environments in which it is impossible to determine the exact goal states ahead of plan execution. GUSSPs introduce flexibility in goal specification by allowing a belief over possible goal configurations. The unique observations at potential goals helps the agent identify the true goal during plan execution. The partial observability is restricted to goals, facilitating the reduction to an SSP with a modified state space. We formally define a GUSSP and discuss its theoretical properties. We then propose an admissible heuristic that reduces the planning time using FLARES -- a start-of-the-art probabilistic planner. We also propose a determinization approach for solving this class of problems. Finally, we present empirical results on a search and rescue mobile robot and three other problem domains in simulation.

And while that was happening, the financial sector was also taking note. Among the many boons of AI tech for finance is the practice called algorithmic trading: the idea that an advanced AI may be able to assist the investors by predicting the market dynamics with enough precision to make consistent profit. And while many advanced machine learning models developed for this purpose stay outside the reach of the general public, others are eager to make AI-driven trading available to a broader audience. One of the leaders in this sphere is the Israel-based company with an ambitious name I Know First. With its powerful cloud-based AI capable of predicting the price dynamics for more than 10,000 financial instruments, including stock ideas, ETFs, world indices, commodities and currencies, it offers its forecasts to private and institutional investors alike.

With the number of Coronavirus cases increasing every day, it is evident that the entire world is struggling to triumph over this deadly disease. While the top health organizations are aiding funds to facilitate research, many believe that the artificial intelligence might help in decelerating the crisis. Let's have a look at how artificial intelligence can help in overcoming this pandemic situation: Artificial Intelligence, aka AI, may see coming pandemics, which will give us sufficient time to prepare. According to Forbes, a Canada based development company had warned of this threat a few days before the authorities issued public warnings. This clearly depicts that the earlier we can track the virus, the better we can fight it.

You'd thinking flying in a plane would be more dangerous than driving a car. In reality it's much safer, partly because the aviation industry is heavily regulated. Airlines must stick to strict standards for safety, testing, training, policies and procedures, auditing and oversight. And when things do go wrong, we investigate and attempt to rectify the issue to improve safety in the future. Other industries where things can go very badly wrong, such as pharmaceuticals and medical devices, are also heavily regulated.

From developing drug treatments to predicting the next hotspot, artificial intelligence may help researchers, healthcare workers, and everyday people offset the impact of the coronavirus. As the worldwide fight against coronavirus COVID-19 continues, companies and governments around the world are pulling out all the stops in an effort to stave off the pandemic's worst impacts. One tool in that toolbox that might prove particularly useful is artificial intelligence (AI). Even though AI has been around since the 1960s, it's only been in the past few years that its adoption outside of science labs and research institutions has really taken off. Perhaps the most common application of AI people have come into contact with today are virtual assistants like Apple's Siri and Amazon's Alexa, which rely on natural language processing (NLP) algorithms to understand human speech.

Stress can lead to poor decision-making, and people hunting for George Clooney's face could help us understand why. Thackery Brown at Stanford University, California, and his colleagues asked 38 people, with an average age of 23, to navigate looping paths around 12 different virtual towns in a simulated environment. Each town had just a few streets and took about a minute to navigate. The researchers also placed the face of a celebrity – George Clooney, for example – at a point along the route. The team then asked the participants to navigate the simulation again while lying inside a functional magnetic resonance imagine (fMRI) machine.

Biomimicry is a tool which can be used while seeking innovation. The concept is that nature has already solved many design problems through the process of evolution. Living things that are still extant have received bits and bytes of code in the form of genetic material and when this information interfaces with the environment, sustainable life forms emerge. Animals, plants, viruses, and bacteria adapt by engineering themselves over the billions of years that life has existed on Earth. The Biomimicry Institute provides numerous examples.