Mastering machine learning is not easy, even if you're a crack programmer. I've seen many people come from a solid background of writing software in different domains (gaming, web, multimedia, etc.) thinking that adding machine learning to their roster of skills is another walk in the park. And every single one of them has been dismayed. I see two reasons for why the challenges of machine learning are misunderstood. First, as the name suggests, machine learning is software that learns by itself as opposed to being instructed on every single rule by a developer.

My name is Usman Iqbal and I am working as an Assistant professor at Taipei Medical University. In this course, you will learn about the application of big data and artificial intelligence in medicine and how data have transformed healthcare today globally. You will also learn about the benefits and challenges of sharing global healthcare data. Data transparency is very important, as data sharing have huge potential for the healthcare improvement and patient safety around the globe. For example, in Taiwan, during the COVID-19, Taiwan's initiative for containing COVID-19 includes linking the National Immigration Agency data with the National Health Insurance data.

In response to calls for greater interdisciplinary involvement from the social sciences and humanities in the development, governance, and study of artificial intelligence systems, this paper presents one sociologist's view on the problem of algorithmic bias and the reproduction of societal bias. Discussions of bias in AI cover much of the same conceptual terrain that sociologists studying inequality have long understood using more specific terms and theories. Concerns over reproducing societal bias should be informed by an understanding of the ways that inequality is continually reproduced in society -- processes that AI systems are either complicit in, or can be designed to disrupt and counter. The contrast presented here is between conservative and radical approaches to AI, with conservatism referring to dominant tendencies that reproduce and strengthen the status quo, while radical approaches work to disrupt systemic forms of inequality. The limitations of conservative approaches to class, gender, and racial bias are discussed as specific examples, along with the social structures and processes that biases in these areas are linked to. Societal issues can no longer be out of scope for AI and machine learning, given the impact of these systems on human lives. This requires engagement with a growing body of critical AI scholarship that goes beyond biased data to analyze structured ways of perpetuating inequality, opening up the possibility for radical alternatives.

Dimension reduction and visualization of high-dimensional data have become very important research topics in many scientific fields because of the rapid growth of data sets with large sample size and/or dimensions. In the literature of dimension reduction and information visualization, linear methods such as principal component analysis (PCA) [7] and classical scaling [17] mainly focus on preserving the most significant structure or maximum variance in data; nonlinear methods such as multidimensional scaling [2], isomap [16], and curvilinear component analysis (CCA) [5] mainly focus on preserving the long or short distances in the high-dimensional space. They generally perform well in preserving the global structure of data but can fail to preserve the local structure. In recent years, the manifold learning methods, such as SNE [6], Laplacian eigenmap [1], LINE [15], LARGEVIS [14], t-SNE [19] [18], and UMAP [10], have gained popularity because of their ability to preserve both the local and some aspects of the global structure of data. These methods generally assume that data lie on a low-dimensional manifold of the high-dimensional input space. They seek to find the manifold that preserves the intrinsic structure of the high-dimensional data. Many of the manifold learning methods suffer from something called the "crowding problem" while preserving local distance of high-dimensional data in low-dimensional space. This means that, if you want to describe small distances in high-dimensional space faithfully, the points with moderate or large distances between them in high-dimensional space are placed too far away from each other in low-dimensional space.

We focus on the problem of how to achieve online continual learning under memory-constrained conditions where the input data may not be known a priori. These constraints are relevant in edge computing scenarios. We have developed an architecture where input processing over data streams and online learning are integrated in a single recurrent network architecture. This allows us to cast metalearning optimization as a mixed-integer optimization problem, where different synaptic plasticity algorithms and feature extraction layers can be swapped out and their hyperparameters are optimized to identify optimal architectures for different sets of tasks. We utilize a Bayesian optimization method to search over a design space that spans multiple learning algorithms, their specific hyperparameters, and feature extraction layers. We demonstrate our approach for online non-incremental and class-incremental learning tasks. Our optimization algorithm finds configurations that achieve superior continual learning performance on Split-MNIST and Permuted-MNIST data as compared with other memory-constrained learning approaches, and it matches that of the state-of-the-art memory replay-based approaches without explicit data storage and replay. Our approach allows us to explore the transferability of optimal learning conditions to tasks and datasets that have not been previously seen. We demonstrate that the accuracy of our transfer metalearning across datasets can be largely explained through a transfer coefficient that can be based on metrics of dimensionality and distance between datasets.

Cross Entropy (CE) has an important role in machine learning and, in particular, in neural networks. It is commonly used in neural networks as the cost between the known distribution of the label and the Softmax/Sigmoid output. In this paper we present a new cost function called the Amended Cross Entropy (ACE). Its novelty lies in its affording the capability to train multiple classifiers while explicitly controlling the diversity between them. We derived the new cost by mathematical analysis and "reverse engineering" of the way we wish the gradients to behave, and produced a tailor-made, elegant and intuitive cost function to achieve the desired result. This process is similar to the way that CE cost is picked as a cost function for the Softmax/Sigmoid classifiers for obtaining linear derivatives. By choosing the optimal diversity factor we produce an ensemble which yields better results than the vanilla one. We demonstrate two potential usages of this outcome, and present empirical results. Our method works for classification problems analogously to Negative Correlation Learning (NCL) for regression problems.

We aim to enable an autonomous robot to learn new skills from demo videos and use these newly learned skills to accomplish non-trivial high-level tasks. The goal of developing such autonomous robot involves knowledge representation, specification mining, and automated task planning. For knowledge representation, we use a graph-based spatial temporal logic (GSTL) to capture spatial and temporal information of related skills demonstrated by demo videos. We design a specification mining algorithm to generate a set of parametric GSTL formulas from demo videos by inductively constructing spatial terms and temporal formulas. The resulting parametric GSTL formulas from specification mining serve as a domain theory, which is used in automated task planning for autonomous robots. We propose an automatic task planning based on GSTL where a proposer is used to generate ordered actions, and a verifier is used to generate executable task plans. A table setting example is used throughout the paper to illustrate the main ideas.

Deep reinforcement learning includes a broad family of algorithms that parameterise an internal representation, such as a value function or policy, by a deep neural network. Each algorithm optimises its parameters with respect to an objective, such as Q-learning or policy gradient, that defines its semantics. In this work, we propose an algorithm based on meta-gradient descent that discovers its own objective, flexibly parameterised by a deep neural network, solely from interactive experience with its environment. Over time, this allows the agent to learn how to learn increasingly effectively. Furthermore, because the objective is discovered online, it can adapt to changes over time. We demonstrate that the algorithm discovers how to address several important issues in RL, such as bootstrapping, non-stationarity, and off-policy learning. On the Atari Learning Environment, the meta-gradient algorithm adapts over time to learn with greater efficiency, eventually outperforming the median score of a strong actor-critic baseline.

Just over a year and a half ago I was sitting at a desk trading stocks, knowing close to nothing about Machine Learning and having last coded in a bit of Matlab 4 years earlier at university. This post hopes to give some resources for someone wanting to make a start on their Machine Learning journey, like I did, starting from zero. First up is getting comfortable with Python. Its by far the most used language in Machine Learning being simple, consistent and easily readable. The Modern Python 3 Bootcamp on Udemy was outstanding and perhaps the best £16.99 I've spent, but there'll a trove of free courses available elsewhere online.

AKA, an artificial intelligence development company, announced a function called "Academy Mode", developed for Pepper to serve in the classroom despite the current situation of COVID-19. Academy Mode is designed specifically for the Softbank Robotics Humanoid robot, Pepper, to fit classroom settings and will be released in Korea, Japan, and China's market first. Since entering Japan's market in 2015, AKA has been working together continuously with Softbank Robotics Japan. In May 2019, AKA became an official reseller of Softbank Robotics China for the Pepper robot. Since then, AKA has been actively developing different functions for Pepper to work better in the English education environment.