Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings

Teaching robots to paint in a manner similar to a human painter is an important task in computer vision. A recent paper on proposes a novel approach to this problem, which tackles several limitations of current algorithms.

Image credit: Plinio Nomellini via Wikimedia (Public Domain)

Like in other methods, reinforcement learning is used to predict a sequence of brush strokes from a given image. However, instead of depicting one single image, the novel method employs a semantic guidance pipeline to learn the distinction between foreground and background brush strokes. Also, a neural alignment model is used to zoom in

Read More

Lancaster statistician to develop revolutionary new AI for use in autonomous cars and cybersecurity

A Lancaster University researcher will conduct ground-breaking Artificial Intelligence (AI) research to revolutionise the use of AI in autonomous vehicles and cybersecurity, as part of a prestigious Turing AI Acceleration Fellowship.

As technology advances, there is a growing need to collect vast quantities of data easily and inexpensively and to use these data to deliver significant benefits across a wide range of applications such as energy consumption and public health.

A key challenge in AI research is to extract meaningful value from these data sources to make decisions that can be trusted and understood to improve the way society functions. 

Read More

Which factors trigger leaf die-off in autumn?

Researchers at ETH Zurich have identified a self-regulating mechanism in European deciduous trees that limit their growing-​season length: Trees that photosynthesise more in spring and summer lose their leaves earlier in autumn.

Leaves of temperate deciduous trees glow in all their yellow and red glory just before falling, signalling that autumn has come. This process, called leaf senescence, allows trees to prepare for the coming winter by suspending their growth and extracting nutrients from the foliage. In the trees’ phenological cycle, leaf senescence marks the end of the productive period during which they absorb CO2 through photosynthesis.

Leaves change

Read More

T-ray technology reveals what is getting under your skin

A new method for analysing the structure of skin using a type of radiation known as T-rays could help improve the diagnosis and treatment of skin conditions such as eczema, psoriasis and skin cancer.

A demonstration of how the T-ray equipment can be used to scan an individual’s skin. Image credit: University of Warwick

Scientists from the University of Warwick and The Chinese University of Hong Kong (CUHK) have shown that using a method that involves analysing T-rays fired from several different angles, they can build a more detailed picture of the structure of an area of skin and how

Read More

Black Silicon Photodetector Breaks the 100% External Quantum Efficiency Limit for the First Time Ever

In a surprising twist, researchers from Aalto University have recently developed a black silicon photodetector that has reached above 130% external quantum efficiency, sending the research team into a brief state of disbelief.

An external quantum efficiency of more than 100% means that one incoming photon generates more than one electron to the external circuit – a phenomenon that hasn’t been observed up until now since the presence of electrical and optical losses has reduced the number of collected electrons.

With new silicone photodectors that exceed 100% external quantum efficiency, light-detecting devices are about to get a massive boost

Read More