Vik Chandra, CEO of uMETHOD, talked with Fox News Digital about how his company's AI tool, RestoreU, is helping physicians pinpoint better treatment plans for their dementia patients. More than six million Americans are living with Alzheimer's disease -- and one in three seniors dies with the disease, according to statistics from the Alzheimer's Association. With so many different factors -- genetics, lifestyle and environment -- influencing a person's risk of developing Alzheimer's, many doctors are moving away from one-size-fits-all approaches and calling for more individualized treatments. It's a concept known as precision medicine. And it's what inspired a company called uMETHOD to create RestoreU, a tool that uses artificial intelligence to help physicians create personalized care plans for patients with Alzheimer's and other types of dementia.

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities of the human mind, according to ibm.com. One of the most important technologies of the 21st century, AI is already being used in dozens of processes, including speech recognition, customer service and automated stock trading. And the economic impact of AI promises to be immense. According to a 2018 report by McKinsey Global Institute, AI has the potential to add 16 percent or around $13 trillion to current global economic output by 2030. Needless to say, it is important for young people to learn about AI and take advantage of the economic and career opportunities it creates.

We introduce an online tensor decomposition based approach for two latent variable modeling problems namely, (1) community detection, in which we learn the latent communities that the social actors in social networks belong to, and (2) topic modeling, in which we infer hidden topics of text articles. We consider decomposition of moment tensors using stochastic gradient descent. We conduct optimization of multilinear operations in SGD and avoid directly forming the tensors, to save computational and storage costs. We present optimized algorithm in two platforms. Our GPU-based implementation exploits the parallelism of SIMD architectures to allow for maximum speed-up by a careful optimization of storage and data transfer, whereas our CPU-based implementation uses efficient sparse matrix computations and is suitable for large sparse datasets. For the community detection problem, we demonstrate accuracy and computational efficiency on Facebook, Yelp and DBLP datasets, and for the topic modeling problem, we also demonstrate good performance on the New York Times dataset. We compare our results to the state-of-the-art algorithms such as the variational method, and report a gain of accuracy and a gain of several orders of magnitude in the execution time.