Collaborating Authors


Understanding TinyML And Its Applications


TinyML is a sort of machine learning in which deep learning networks are shrunk to fit on a piece of hardware. Artificial Intelligence and intelligent gadgets are combined in this project. In your pocket lies 45x18mm of Artificial Intelligence. Suddenly, your Arduino board's do-it-yourself weekend project has a little machine learning model implanted in it. New embedded machine learning frameworks will enable the spread of AI-powered IoT devices.

A Deep Learning Model to Predict Sepsis Early


The increased adoption of EHRs in hospitals has led to the development of machine learning-based surveillance tools to detect and predict sepsis.

Pneumonia Detection:


Build a deep learning model that can detect Pneumonia from patients' chest X-Ray images. Below is the high-level approach on how I created the deep learning model. I first collected the data from Kaggle, which are chest X-Ray images of patients from China. Then, I moved onto creating the architecture of convolutional neural network (CNN) model, which is a type of deep learning model. Data, obtained from Kaggle, contains 5,856 chest X-Ray images of pediatric patients under age of 5 from a medical center in Guangzhou, China.

A Nutrition Label for AI


It can be difficult to understand exactly what's going on inside of a deep learning model, which is a real problem for companies concerned about bias, ethics, and explainability. Now IBM is developing something called AI FactSheets, which it describes as a nutrition label for deep learning that explains how models work and that can also detect bias. AI FactSheets is a new addition to Watson Open Scale that will provide a plain-language description of what's going on inside deep learning models. The software, which is expected to be generally available soon, can work with AI models developed by Watson Studio, or any other AI model accessible from a REST API. After being exposed to the model, AI FactSheets generates a PDF with information about bias, trust, and transparency aspects of a given deep learning model.

The GPT-3 economy


Since its release, GPT-3, OpenAI's massive language model, has been the topic of much discussion among developers, researchers, entrepreneurs, and journalists. Most of those discussions have been focused on the capabilities of the AI-powered text generator. But much about GPT-3 remains obscure. The company has opted to commercialize the deep learning model instead of making it freely available to the public. And though the AI has shown to be capable of many interesting feats, it's not yet clear if GPT-3 will become a real product or will join the endless array of abandoned projects that never found a viable business model. Earlier this month, as reported by users who have access to the beta version of the language model, OpenAI declared the initial pricing plan of GPT-3.

Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework Machine Learning

Deep learning has achieved incredible success over the past years, especially in various challenging predictive spatio-temporal analytics (PSTA) tasks, such as disease prediction, climate forecast, and traffic prediction, where intrinsic dependency relationships among data exist and generally manifest at multiple spatio-temporal scales. However, given a specific PSTA task and the corresponding dataset, how to appropriately determine the desired configuration of a deep learning model, theoretically analyze the model's learning behavior, and quantitatively characterize the model's learning capacity remains a mystery. In order to demystify the power of deep learning for PSTA, in this paper, we provide a comprehensive framework for deep learning model design and information-theoretic analysis. First, we develop and demonstrate a novel interactively- and integratively-connected deep recurrent neural network (I$^2$DRNN) model. I$^2$DRNN consists of three modules: an Input module that integrates data from heterogeneous sources; a Hidden module that captures the information at different scales while allowing the information to flow interactively between layers; and an Output module that models the integrative effects of information from various hidden layers to generate the output predictions. Second, to theoretically prove that our designed model can learn multi-scale spatio-temporal dependency in PSTA tasks, we provide an information-theoretic analysis to examine the information-based learning capacity (i-CAP) of the proposed model. Third, to validate the I$^2$DRNN model and confirm its i-CAP, we systematically conduct a series of experiments involving both synthetic datasets and real-world PSTA tasks. The experimental results show that the I$^2$DRNN model outperforms both classical and state-of-the-art models, and is able to capture meaningful multi-scale spatio-temporal dependency.

Machine learning tool may help us better understand RNA viruses


E2Efold is an end-to-end deep learning model developed at Georgia Tech that can predict RNA secondary structures, an important task used in virus analysis, drug design, and other public health applications.