Editor's note: Maggie is a speaker for ODSC APAC 2021. Check out her talk, "How to Get Started With Deep Reinforcement Learning on a Variety of Use Cases?" there! I, like many others, first heard of reinforcement learning (RL) in the context of games. I watched a documentary about AlphaGo winning against Lee Sedol, the world Go champion, which, I must admit, made me shed a tear or two. However, when the opportunity emerged to try to apply RL in my work, a whole bunch of new questions flew into my mind.

The increase in cancer cases, the democratization of healthcare, even the recent pandemic, are some of the numerous reasons pointing out that there is a great need in leveraging AI technology in patients' care practice. However, while AI has demonstrated the capability to be a valuable companion to practitioners, with respect to meeting accuracy levels, removing bias and increasing diagnostic throughput, its adoption to clinical practice is still slow. While the problem is more complex, in this instructional workshop we will focus on two critical aspects of adoption. AI technologies, notably deep learning techniques, may hide inherent risks such as the codification of biases, the weak accountability and the bare transparency of their decision-making process. AI technology needs to both improve the diagnostic power of the data processed but also provide evidence for the prediction in a user understandable way.

This piece was the winner of the inaugural Gradient Prize. AI systems are compute-intensive: the AI lifecycle often requires long-running training jobs, hyperparameter searches, inference jobs, and other costly computations. They also require massive amounts of data that might be moved over the wire, and require specialized hardware to operate effectively, especially large-scale AI systems. All of these activities require electricity -- which has a carbon cost. There are also carbon emissions in ancillary needs like hardware and datacenter cooling [1]. Thus, AI systems have a massive carbon footprint[2].

Many real-world applications of Machine Learning involve making predictions about the outcomes of a group of related variables based on historical context. We might want to forecast the traffic conditions on connected roads, the weather at nearby locations, or the demand for similar products. By modeling multiple time series together, we hope that changes in one variable may reveal key information about the behavior of related variables. Multivariate Time Series Forecasting (TSF) datasets have two axes of difficulty: we need to learn temporal relationships to understand how values change over time and spatial relationships to know how variables impact one another. Popular statistical approaches to TSF can struggle to interpret long context sequences and scale to complex variable relationships.

What does it mean to be first in developing applications of artificial intelligence (AI), and does it matter? In a recent interview, the former Chief Software Officer of the U.S. Air Force Nicolas Chaillan stated that he resigned in part because he believed that, "We have no competing chance against China in fifteen to twenty years. Right now, it's already a done deal; it is already over." He reasoned that a failure of the U.S. Department of Defense (DoD) to follow through on stated intentions to build up in AI and cyber means many departments within DoD still operate at what Chaillan considers a "kindergarten level." Those are strong words, but Chaillan's overall assessment misses the mark--the United States becoming an AI also-ran is not a foregone conclusion.

The open-source software developer GitHub says as much as 30% of newly written code on its network is being done with the help of the company's AI programming tool Copilot. Why it matters: Copilot can look at code written by a human programmer and suggest further lines or alternative code, eliminating some of the repetitive labor that goes into coding. How it works: Copilot is built on the OpenAI Codex algorithm, which was trained on terabytes of openly available source code and can translate human language into programming language. It serves as a more sophisticated autocomplete tool for programmers.

TensorFlow is one of the most widely used open-source library for machine learning and deep learning applications built by Google. TensorFlow 2.0 is the official second version of this library that encompasses many changes to make users more productive. Some major features highlights of TensorFlow 2.0 are: You can read more about the changes TensorFlow 2.0 encompasses in this TensorFlow's official blog. Learn how to build Machine Learning projects using TensorFlow 2.0? Enroll in this TensorFlow Course created by The Click Reader.

Said Vladimir Puzyrev of Curtin Universitys Oil and Gas Innovation Centre and the School of Earth and Planetary Sciences, "This project is an important step towards adding value to existing digital geochemical datasets." Researchers at Australia's Curtin University and the Geological Survey of Western Australia are using deep learning to analyze geochemical data as part of an effort to expand mineral exploration in the region. The Western Australia Mineral Exploration (WAMEX) database contains more than 50 million samples, making manual analysis cost prohibitive and time consuming. Curtin's Vladimir Puzyrev said, "The ultimate aim of this research project is to help identify new mineral deposits in Western Australia by analyzing big geochemical data using deep learning methods."

This paper proposes an efficient way to reduce usage or predict the future needs of appliances or power consumption by using the weather information data . Over the last few years, activity recognition in the smart home has become an active research area due to the wide range of human centric-applications. IoT brings together everything at home under one umbrella which has the potential to monitor and remote control such as air conditioning, alarm system, lighting, heating, ventilation, telephone system, tv, etc. To enhance our comfort and security with low energy consumption and energy management is one of the IoT use cases with which energy being sent out or consumed can be monitored. One can monitor each of the IoT appliances and how much power each of the devices is consuming, and easily switch between energy-efficient appliances across the day. In this case study we are going to focus on predicting the future energy consumption with the past data so that we can manage our day to day usage of appliances at home.

Supervised learning is the common most type of machine learning. Most ML problems that we encounter fall into this category. As the name implies, a supervised learning algorithm is trained with input data along with some form of guidance that we can call labels. Labels are also known as targets and they act as a description of the input data. With that said, there are other advanced tasks that don't directly fall into supervised learning, but they actually are.