Abstract--A Deep Autoencoder based content retrieval algorithm is proposed for prediction and differentiation of cancer types based on the presence of epigenetic patterns of DNA methylation identified in genetic regions known as CpG islands. The developed deep learning system uses a CpG island state classification subsystem to complete sets of missing/incomplete island data in given human cell lines, and is then pipelined with an intricate set of statistical and signal processing methods to accurately predict the presence of cancer and further differentiate the type and cell of origin in the event of a positive result. The proposed system was trained with previously reported data derived from four case groups of cancer cell lines, achieving overall Sensitivity of 88.24%, Specificity of 83.33%, Accuracy of 84.75% and Matthews Correlation Coefficient of 0.687. The ability to predict and differentiate cancer types using epigenetic events as the identifying patterns was demonstrated in previously reported data sets from breast, lung, lymphoblastic leukemia and urological cancer cell lines, allowing the pipelined system to be robust and adjustable to other cancer cell lines or epigenetic events. Significant progress has been made in understanding crucial regulatory mechanisms responsible for the development and progression of cancer at a cellular and molecular level, through genetic alterations such as DNA mutations and disruptions in epigenetic mechanisms including DNA methylation and histone modifications [1]. Cancer rates have been progressively increasing, with the latest statistics from Cancer Research UK to have reported more than 350,000 new cases diagnosed in the UK [2], of which more than 40% could have been prevented. Cancer research has been significantly progressing with advances in more effective treatments and screening methods, however there is still a pressing need for more targeted methods to be available for monitoring of cancer progression and prevention of treatment resistance that would help control the disease and improve survival rates.

We describe a framework of hybrid cognition by formulating a hybrid cognitive agent that performs hierarchical active inference across a human and a machine part. We suggest that, in addition to enhancing human cognitive functions with an intelligent and adaptive interface, integrated cognitive processing could accelerate emergent properties within artificial intelligence. To establish this, a machine learning part learns to integrate into human cognition by explaining away multi-modal sensory measurements from the environment and physiology simultaneously with the brain signal. With ongoing training, the amount of predictable brain signal increases. This lends the agent the ability to self-supervise on increasingly high levels of cognitive processing in order to further minimize surprise in predicting the brain signal. Furthermore, with increasing level of integration, the access to sensory information about environment and physiology is substituted with access to their representation in the brain. While integrating into a joint embodiment of human and machine, human action and perception are treated as the machine's own. The framework can be implemented with invasive as well as non-invasive sensors for environment, body and brain interfacing. Online and offline training with different machine learning approaches are thinkable. Building on previous research on shared representation learning, we suggest a first implementation leading towards hybrid active inference with non-invasive brain interfacing and state of the art probabilistic deep learning methods. We further discuss how implementation might have effect on the meta-cognitive abilities of the described agent and suggest that with adequate implementation the machine part can continue to execute and build upon the learned cognitive processes autonomously.

Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep reinforcement learning (Deep RL), such optimization methods are often used for training neural networks via the temporal difference error or policy gradient. As an agent improves over time, the optimization target changes and thus the loss landscape (and local optima) change. Due to the failure modes of those methods, the ideal choice of optimizer for Deep RL remains unclear. As such, we provide an empirical analysis of the effects that a wide range of gradient descent optimizers and their hyperparameters have on policy gradient methods, a subset of Deep RL algorithms, for benchmark continuous control tasks. We find that adaptive optimizers have a narrow window of effective learning rates, diverging in other cases, and that the effectiveness of momentum varies depending on the properties of the environment. Our analysis suggests that there is significant interplay between the dynamics of the environment and Deep RL algorithm properties which aren't necessarily accounted for by traditional adaptive gradient methods. We provide suggestions for optimal settings of current methods and further lines of research based on our findings.

When looking for examples of digital innovation, few of us would think of public transport. But it turns out the sector is a rich source of use cases for big data, open APIs and even artificial intelligence. In a major city like London or Paris, there are millions of travelers every day who need accurate, timely information about the current schedules of thousands of buses, trams and trains. Getting that information to them on their smartphones has taken a lot of foresight, creativity and graft over the years, and the innovation continues today. In one example launched in Britain last month, rail booking service Trainline has begun using AI to generate personalized alerts about travel disruption to users of its mobile app.

The future of smartphones might not be flashy technology like augmented reality, but a device that actually takes a page from the real world - at least, if one researcher has his way. Marc Teyssier, a PhD student at the University of Paris-Saclay in France, has developed the'MobiLimb,' a robotic finger that turns into a phone accessory when it's plugged into a USB port. It serves as a literal helping hand, functioning as a phone stand, extra grip to hold onto your phone or a way to act out emojis. The robotic finger is fitted with a series of actuators and sensors that allow it to move and interact with users. Actuators, or motors, are mounted in each link of the finger to give it a full range of motion.

New biomedical techniques, such as next-generation genome sequencing, are creating vast amounts of data and transforming the scientific landscape. They're leading to unimaginable breakthroughs -- but leaving researchers racing to keep up. "This is when I start feeling my age," Anne Corcoran says. Corcoran leads a group that looks at how our genomes -- the DNA coiled in almost every cell in our bodies -- relate to our immune systems, and specifically to the antibodies we make to defend against infection. She is, in her own words, an "old-school biologist," brought up on the skills of pipettes and Petri dishes and protective goggles, the science of experiments with glassware on benches -- what's known as'wet lab' work. "I knew what a gene looked like on a gel," she says, thinking back to her early career. These days, that skill set is not enough. "When I started hiring Ph.D. students 15 years ago, they were entirely wet lab," Corcoran says. "Now when we recruit them, the first thing we look for is if they can cope with complex bioinformatic analysis."

On the heels of its dual announcement at the Open Compute Project Summit in Amsterdam this week (see related story), Xilinx yesterday disclosed that AMD and Xilinx have teamed to set an AI inference processing record of 30,000 images per second. The joint work of the two companies, announced at the Xilinx Developer Forum in San Jose by Xilinx CEO Victor Peng and AMD CTO Mark Papermaster, connects AMD's EPYC CPUs and the new Xilinx Alveo FPGA accelerator card, announced yesterday at the OCP Summit. The record, running a batch size of 1 and Int8 precision, was accomplished on a system that leverages two AMD EPYC 7551 server CPUs with PCIe connectivity, along with eight Alveo U250 accelerator cards. In a blog post, Xilinx said the inference performance is powered by Xilinx ML Suite, which allows developers to optimize and deploy accelerated inference and supports various machine learning frameworks, such as TensorFlow. The benchmark was performed on the GoogLeNet convolutional neural network.

A scientist has built a Rubik's cube that can solve itself. The toy, which has a 3D-printed robotic core, creepily completes its own iconic puzzle in just 30 seconds. Containing two internal servo motors, the entire system runs on a micro-controlling Arduino board which is small enough to fit inside the original product's dimensions. The new incarnation of the game, which first launched in 1974, is the product of Japanese creator and YouTube vlogger the'human controller'. Uploading footage of his creation, last month, the impressive scenes - which show the cube flipping and self-rotating - has already racked-up nearly 500,000 views.

Raygorodskaya has had a busy year since her seven-year-old travel-booking startup, Wanderu, reached profitability in August 2017. Not only is her Boston-based company on pace to close 2018 with more than $200 million in revenue--double what it did last year--but it has also expanded its service internationally, now covering 130 million routes between 11,000 cities in 60 countries across North America and Europe. Wanderu lets customers book travel itineraries from point A to point B using different modes of transportation like buses and trains. By the end of the year, Raygorodskaya says, users will be able to book bus, train, ferry, and airplane tickets with a single Wanderu search--a service not yet offered by any other business. "Reaching profitability is one major feat, but it's really tough to maintain it," says the 32-year-old Russian immigrant.

World Space Week begins today, Thursday 4 October – a global series of global events hosted by the United Nations. This year's theme: 'Space unites the world'. Three new reports published today by the UK Space Agency emphasise how the potential of the space industry lies in not just in gazing out from Earth to the cosmos, but also in looking back to Earth from orbit in order to solve terrestrial problems. The reports reveal how the industry can help to save lives and livelihoods from natural disasters, address the major challenges confronting the agriculture sector, and deliver better management of forests to improve production and protect nature on a global scale. The first document, Space for Disaster Resilience in Developing Countries, explains how the space sector is well placed to contribute new types of information.