Georgia Institute of Technology

Machine learning has been around for decades, but the advent of big data and more powerful computers has increased its impact significantly — ­moving machine learning beyond pattern recognition and natural language processing into a broad array of scientific disciplines. A subcategory of artificial intelligence, machine learning deals with the construction of algorithms that enable computers to learn from and react to data rather than following explicitly programmed instructions.

A nanostructured gate dielectric may have addressed the most significant obstacle to expanding the use of organic semiconductors for thin-film transistors. The structure, composed of a fluoropolymer layer followed by a nanolaminate made from two metal oxide materials, serves as gate dielectric and simultaneously protects the organic semiconductor – which had previously been vulnerable to damage from the ambient environment – and enables the transistors to operate with unprecedented stability.

A discovery by researchers from Princeton University, the Georgia Institute of Technology and Humboldt University in Berlin points the way to more widespread use of an advanced technology generally known as organic electronics. The research, published in the journal Nature Materials, focused on organic semiconductors, a class of materials prized for their applications in emerging technologies such as flexible electronics, solar energy conversion, and high-quality colour displays for smartphones and televisions.

A transfer technique based on thin sacrificial layers of boron nitride could allow high-performance gallium nitride gas sensors to be grown on sapphire substrates and then transferred to metallic or flexible polymer support materials. The technique could facilitate the production of low-cost wearable, mobile and disposable sensing devices for a wide range of environmental applications.

A team of Georgia Tech researchers is bringing electronic design software and communications expertise to DARPA's new CHIPS initiative, which will enable future generations of integrated circuits to be assembled from plug-and-play modules known as “chiplets.” Reusing blocks of existing microelectronics technology could reduce the need to design complex monolithic chips from scratch for new applications.

The nation’s first remote robotics lab, and the nearly 100 machines that call it home, is now open thanks to a little help from its friends. The Robotarium held its grand opening on Tuesday in the Van Leer Building. Appropriately, a scissor-wielding robot (named Snips) cut the ribbon. Later, a researcher from the University of Illinois at Urbana-Champaign skyped into the room to run a live remote experiment.

Cities have been around for thousands of years, so urbanisation is hardly a new phenomenon — but it’s happening now at an unprecedented pace. In 1950 about 30% of the world’s population lived in cities, a number that shot up to nearly 55% by 2016 and is expected to hit 60% by 2030, according to United Nations statistics. This dramatic growth brings challenges on a variety of fronts, transforming 'smart cities' from a catchy phrase into a critical endeavour.

A marimba-playing robot with four arms and eight sticks is writing and playing its own compositions in a lab at the Georgia Institute of Technology. The pieces are generated using artificial intelligence and deep learning. Researchers fed the robot nearly 5,000 complete songs — from Beethoven to the Beatles to Lady Gaga to Miles Davis — and more than 2 million motifs, riffs and licks of music.

A team of researchers at Georgia Institute of Technology and University of Notre Dame has created a computing system that aims to tackle one of computing’s hardest problems in a fraction of the time. “We wanted to find a way to solve a problem without using the normal binary representations that have been the backbone of computing for decades,” said Arijit Raychowdhury, an associate professor in Georgia Tech’s School of Electrical and Computer Engineering.

The traditional interface for remotely operating robots works just fine for roboticists. They use a computer screen and mouse to independently control six degrees of freedom, turning three virtual rings and adjusting arrows to get the robot into position to grab items or perform a specific task. But for someone who isn’t an expert, the ring-and-arrow system is cumbersome and error-prone. It’s not ideal, for example, for older people trying to control assistive robots at home.

Using massive data sets, machine learning, and high-performance computing, health analytics and informatics is drawing us closer to the holy grail of health care: precision medicine, which promises diagnosis and treatment tailored to individual patients. The information, including findings from the latest peer-reviewed studies, will arrive on the desktops and mobile devices of clinicians in health care facilities large and small through a new generation of decision-support systems.

Doctors knew long before Owen Webb was born that they were racing against the clock to save his life. Tests had confirmed the developing child suffered from Krabbe disease, a genetic disorder that causes toxins to build up in the nervous system, progressively damaging the brain. Just days after he was delivered, a medical team at Duke University began Owen on nine days of chemotherapy. His body was then infused with stem cell-rich donor umbilical cord blood.

  The Georgia Institute of Technology has been awarded a $17.3 million cyber security research contract to help establish new science around the ability to quickly, objectively and positively identify the virtual actors responsible for cyberattacks, a technique known as "attribution."

When a microscopic lab worm grows an eye-popping oddity, scientists locate the mutated gene that caused it. It’s truly interesting. Yet, more important findings, medically relevant ones, may be hiding in traits invisible to the eye, even with the best microscope. Researchers at the Georgia Institute of Technology are exposing these secrets - micron-sized bumps and grooves - and the intricate web of gene mutations possibly behind them in high detail. Their work could prove useful to understanding debilitating disorders.

In the fight against cancer, doctors dish out combination-blows of surgery, chemotherapy and other drugs to beat back a merciless foe. Now, scientists have taken early steps toward adding a stinging punch to clinicians' repertoire. A novel targeted therapy using nanoparticles has enabled researchers at the Georgia Institute of Technology to purge ovarian tumors in limited, in vivo tests in mice.

For scientists listening in on the faint whispers of brain neurons, a first-ever robotic technique for cleaning the tiny devices that record the signals could facilitate a new level of automation in neuroscience research. That could accelerate the gathering of information used to map the functions of brain cells and ultimately provide a better understanding what’s going on between our ears.

Bleeding disorders could one day be diagnosed by putting platelets through strength tests, researchers have proposed. Biomedical engineers from Emory University and the Georgia Institute of Technology have devised a microfluidic testing ground where platelets can demonstrate their strength by squeezing two protein dots together. Imagine rows and rows of strength testing machines from a carnival, but very tiny. A platelet is capable of exerting forces that are several times larger, in relation to its size, than a muscle cells.

When roboticists create behaviors for teams of robots, they first build algorithms that focus on the intended task. Then they wrap safety behaviors around those primary algorithms to keep the machines from running into each other. Each robot is essentially given an invisible bubble that other robots must stay away from. As long as nothing touches the bubble, the robots move around without any issues. But that's where the problems begin.

Using a unique single-molecule force measurement tool, a research team has developed a clearer understanding of how platelets sense the mechanical forces they encounter during bleeding to initiate the cascading process that leads to blood clotting. Beyond providing a better understanding of this vital bodily process, research into a mechanoreceptor molecule that triggers clotting could provide a potential new target for therapeutic intervention.

Georgia Institute of Technology researchers have created what they say is the most efficient-walking humanoid ever created. While most machines these days are hunched at the waist and plod along on flat feet, Georgia Tech's DURUS strolls like a person. Its legs and chest are elongated and upright. It lands on the heel of its foot, rolls through the step and pushes off its toe. It's even outfitted with a pair of size-13 trainers as it walks under its own power on a treadmill in the team's AMBER Lab.