This is a detailed tutorial paper which explains the Fisher discriminant Analysis (FDA) and kernel FDA. We start with projection and reconstruction. Then, one- and multi-dimensional FDA subspaces are covered. Scatters in two- and then multi-classes are explained in FDA. Then, we discuss on the rank of the scatters and the dimensionality of the subspace. A real-life example is also provided for interpreting FDA. Then, possible singularity of the scatter is discussed to introduce robust FDA. PCA and FDA directions are also compared. We also prove that FDA and linear discriminant analysis are equivalent. Fisher forest is also introduced as an ensemble of fisher subspaces useful for handling data with different features and dimensionality. Afterwards, kernel FDA is explained for both one- and multi-dimensional subspaces with both two- and multi-classes. Finally, some simulations are performed on AT&T face dataset to illustrate FDA and compare it with PCA.

We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science. As of June 20th 2019, the dataset comprises of 12 quantum mechanical properties of 119,487 organic molecules with up to 14 heavy atoms, sampled from the GDB MedChem database. The Alchemy dataset expands the volume and diversity of existing molecular datasets. Our extensive benchmarks of the state-of-the-art graph neural network models on Alchemy clearly manifest the usefulness of new data in validating and developing machine learning models for chemistry and material science. We further launch a contest to attract attentions from researchers in the related fields. More details can be found on the contest website \footnote{https://alchemy.tencent.com}. At the time of benchamrking experiment, we have generated 119,487 molecules in our Alchemy dataset. More molecular samples are generated since then. Hence, we provide a list of molecules used in the reported benchmarks.

The interpretability of machine learning, particularly for deep neural networks, is strongly required when performing decision-making in a real-world application. There are several studies that show that interpretability is obtained by replacing a non-explainable neural network with an explainable simplified surrogate model. Meanwhile, another approach to understanding the target system is simulation modeled by human knowledge with interpretable simulation parameters. Recently developed simulation learning based on applications of kernel mean embedding is a method used to estimate simulation parameters as posterior distributions. However, there was no relation between the machine learning model and the simulation model. Furthermore, the computational cost of simulation learning is very expensive because of the complexity of the simulation model. To address these difficulties, we propose a ``model bridging'' framework to bridge machine learning models with simulation models by a series of kernel mean embeddings. The proposed framework enables us to obtain predictions and interpretable simulation parameters simultaneously without the computationally expensive calculations associated with simulations. In this study, we investigate a Bayesian neural network model with a few hidden layers serving as an un-explainable machine learning model. We apply the proposed framework to production simulation, which is important in the manufacturing industry.

Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a fundamentally new type of method - Beneficial Perturbation Network (BPN). We add task-dependent memory (biasing) units to allow the network to operate in different regimes for different tasks. We compute the most beneficial directions to train these units, in a manner inspired by recent work on adversarial examples. At test time, beneficial perturbations for a given task bias the network toward that task to overcome catastrophic forgetting. BPN is not only more parameter-efficient than network expansion methods, but also does not need to store any data from previous tasks, in contrast with episodic memory methods. Experiments on variants of the MNIST, CIFAR-10, CIFAR-100 datasets demonstrate strong performance of BPN when compared to the state-of-the-art.

There's no escaping A.I., which continues to revolutionize every aspect of our lives -- from microtargeted ads to GPS-based wayfinding apps to highly personalized services. These innovations ride on waves of user information and data of unprecedented volume, leading to a sense of urgency among governments worldwide to figure out how to navigate these uncharted waters. According to Urs Gasser, executive director of the Berkman Klein Center for Internet & Society at Harvard University, there are three archetypal strategies. The U.S.'s laissez-faire approach prioritizes innovation, and lawmakers intervene only when things go wrong. In the European Union, the precautionary principle -- which puts citizen protection, ethics and responsible management before tech innovation -- underpins the General Data Protection Regulation, which was launched in May 2018. Meanwhile, China is mostly concerned about the ways in which A.I. might affect existing social, political and economic relationships.

An artificial intelligence (AI) algorithm can transform low-dose CT (LDCT) scans into high-quality exams that radiologists may even prefer over LDCT studies produced via commercial iterative reconstruction techniques (Nature Machine Intelligence 10.1038/s42256-019-0057-9). A team of researchers from Rensselaer Polytechnic Institute (RPI) in Troy, NY, and Massachusetts General Hospital (MGH) in Boston developed a deep-learning model called a modularized adaptive processing neural network (MAP-NN), which progressively reduces noise on LDCT images with guidance from the radiologist until the optimal level of image quality is achieved. Testing on images from three different vendors, three radiologists found the algorithm produced images that were either better or comparable to images processed with iterative reconstruction. The deep-learning method also processed images much faster. "The deep-learning approach can thus already effectively compete with iterative reconstruction solutions and potentially replace the iterative reconstruction approach," wrote the group, led by Hongming Shan of RPI.

If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. Today is the first day of summer, which means spring is officially over. Come to think of it, I'm not into summer, fall, or winter cleaning either. The trouble with that is I try to avoid vacuuming and sweeping at all costs, and at this point there's probably enough crumbs on my floor to make a surprise casserole.

Regardless of the industry that you're in, it is harder than ever to find truly new customer insights. Research budgets are smaller, the low-hanging fruit has already been picked so you need to dig deeper to find new insights, and traditional research can be expensive and time-consuming. But artificial intelligence, or machine learning, is changing the game, according to John Mitchell, president and managing principal at Applied Marketing Science, a Waltham, MA-based research and marketing firm that helps its clients better understand and incorporate the voice of the customer into product development. Between social media, online customer reviews, and customer service calls, companies already have billions of user-generated content (UGC). "Consumers are freely volunteering insights about products and services at the moment of truth," Mitchell told BIOMEDevice Boston attendees on Tuesday. The problem is that sifting through all of that to find valuable product development insights is simply too much for one human reader to process on their own, Mitchell said.

Global retail technology spending will near $203.6 billion in 2019 as stores continue to play digital catch-up and AI, robotics and payment innovation plans advance. That's according to new research conducted by Tech. a collaboration between Retail Week and World Retail Congress. The surge – an anticipated 3.6% increase from 2018 – comes as owners of physical stores strive to add an advanced digital dimension to offline shopping, among other priorities. The need to engage customers in new ways, while managing stock, operations and promotions more effectively and cost-efficiently, is also driving up international IT spending. The report, "A world in motion: Retail digital transformation across the globe, and the technology supporting it," also identifies country-specific trends.

In 2016, the Johannesburg team at IBM Research discovered that the process of reporting cancer data to the government, which used it to inform national health policies, took four years after diagnosis in hospitals. In the US, the equivalent data collection and analysis takes only two years. The additional lag turned out to be due in part to the unstructured nature of the hospitals' pathology reports. Human experts were reading each case and classifying it into one of 42 different cancer types, but the free-form text on the reports made this very time-consuming. So the researchers went to work on a machine-learning model that could label the reports automatically.