Machine learning-based analysis of medical images often faces several hurdles, such as the lack of training data, the curse of dimensionality problem, and the generalization issues. One of the main difficulties is that there exists computational cost problem in dealing with input data of large size matrices which represent medical images. The purpose of this paper is to introduce a framelet-pooling aided deep learning method for mitigating computational bundle, caused by large dimensionality. By transforming high dimensional data into low dimensional components by filter banks with preserving detailed information, the proposed method aims to reduce the complexity of the neural network and computational costs significantly during the learning process. Various experiments show that our method is comparable to the standard unreduced learning method, while reducing computational burdens by decomposing large-sized learning tasks into several small-scale learning tasks.

The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy when an extremely small amount of labelled data is available has yet to be tackled. In this work, we introduce a novel semi-supervised framework for X-ray classification which is based on a graph-based optimisation model. To the best of our knowledge, this is the first method that exploits graph-based semi-supervised learning for X-ray data classification. Furthermore, we introduce a new multi-class classification functional with carefully selected class priors which allows for a smooth solution that strengthens the synergy between the limited number of labels and the huge amount of unlabelled data. We demonstrate, through a set of numerical and visual experiments, that our method produces highly competitive results on the ChestX-ray14 data set whilst drastically reducing the need for annotated data.

In spite of the rapidly increasing number of applications of machine learning in various domains, a principled and systematic approach to the incorporation of domain knowledge in the engineering process is still lacking and ad hoc solutions that are difficult to validate are still the norm in practice, which is of growing concern not only in mission-critical applications. In this note, we introduce Probabilistic Approximate Logic (PALO) as a logic based on the notion of mean approximate probability to overcome conceptual and computational difficulties inherent to strictly probabilistic logics. The logic is approximate in several dimensions. Logical independence assumptions are used to obtain approximate probabilities, but by averaging over many instances of formulas a useful estimate of mean probability with known confidence can usually be obtained. To enable efficient computational inference, the logic has a continuous semantics that reflects only a subset of the structural properties of classical logic, but this imprecision can be partly compensated by richer theories obtained by classical inference or other means. Computational inference, which refers to the construction of models and validation of logical properties, is based on Stochastic Gradient Descent (SGD) and Markov Chain Monte Carlo (MCMC) techniques and hence another dimension where approximations are involved. We also present the Logical Imagination Engine (LIME), a prototypical implementation of PALO based on TensorFlow. Albeit not limited to the biological domain, we illustrate its operation in a quite substantial bioinformatics machine learning application concerned with network synthesis and analysis in a recent DARPA project.

Lung sounds auscultation is the first and most common examination carried out by every general practitioner or family doctor. It is fast, easy and well known procedure, popularized by La ennec (Hy-acinthe, 1819), who invented the stethoscope. Nowadays, different variants of such tool can be found on the market, both analog and electronic, but regardless of the type of stethoscope, this process still is highly subjective. Indeed, an auscultation normally involves the usage of a stethoscope by a physician, thus relying on the examiner's own hearing, experience and ability to interpret psychoacoustical features. Another strong limitation of standard auscultation can be found in the stethoscope itself, since its frequency response tends to attenuate frequency components of the lung sound signal above nearly 120 Hz, leaving lower frequency bands to be analyzed and to which the human ear is not really sensitive (Sovijrvi et al., 2000) (Sarkar et al., 2015).

While the role of humans is increasingly recognized in machine learning community, representation of and interaction with models in current human-in-the-loop machine learning (HITL-ML) approaches are too low-level and far-removed from human's conceptual models. We demonstrate HEIDL, a prototype HITL-ML system that exposes the machine-learned model through high-level, explainable linguistic expressions formed of predicates representing semantic structure of text. In HEIDL, human's role is elevated from simply evaluating model predictions to interpreting and even updating the model logic directly by enabling interaction with rule predicates themselves. Raising the currency of interaction to such semantic levels calls for new interaction paradigms between humans and machines that result in improved productivity for text analytics model development process. Moreover, by involving humans in the process, the human-machine co-created models generalize better to unseen data as domain experts are able to instill their expertise by extrapolating from what has been learned by automated algorithms from few labelled data. 1 Introduction Machine learning (ML) is an inherently iterative process where humans, ML experts, play a central role.

Microsoft is investing $1 billion in OpenAI to support us building artificial general intelligence (AGI) with widely distributed economic benefits. We're partnering to develop a hardware and software platform within Microsoft Azure which will scale to AGI. We'll jointly develop new Azure AI supercomputing technologies, and Microsoft will become our exclusive cloud provider--so we'll be working hard together to further extend Microsoft Azure's capabilities in large-scale AI systems. Each year since 2012, the world has seen a new step function advance in AI capabilities. Though these advances are across very different fields like vision (2012), simple video games (2013), machine translation (2014), complex board games (2015), speech synthesis (2016), image generation (2017), robotic control (2018), and writing text (2019), they are all powered by the same approach: innovative applications of deep neural networks coupled with increasing computational power.

Docker is everywhere in the software industry today. Mostly popular as a DevOps tool, Docker has stolen the hearts of many developers, system administrators and engineers, among others. "Docker is a tool that helps users to exploit operating-system-level virtualisation to develop and deliver software in packages called containers." This technical definition may sound complicated, but all you need to know is that Docker is a complete environment where you can build and deploy software. It is just like your Linux machine, except that it is very lightweight, fast and has nothing except what you need for your project or software to run without a glitch. One of the best things about Docker is that you can move it across platforms and still run without installing a single dependency -- because all you need is a Docker Engine.

IBM recently developed three artificial intelligence tools that could help medical researchers fight cancer. Now, the company has decided to make all three tools open-source, meaning scientists will be able to use them in their research whenever they please, according to ZDNet. The tools are designed to streamline the cancer drug development process and help scientists stay on top of newly-published research -- so, if they prove useful, it could mean more cancer treatments coming through the pipeline more rapidly than before. This week, IBM scientists are presenting the three AI tools at two molecular biology conferences in Switzerland, according to an IBM press release. The first, PaccMann, uses deep learning algorithms to predict whether compounds will be viable anticancer drugs, taking some of the expensive guesswork out of pharmaceutical development, according to the press release.

In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven health monitoring systems is gaining in popularity due to the large availability of data from low-cost sensors with internetworking capabilities. In particular, deep learning provides the tools for processing and analyzing this unprecedented amount of data efficiently. The main purpose of this paper is to combine the recent advances of Deep Learning (DL) and statistical analysis on structural health monitoring (SHM) to develop an accurate classification tool able to discriminate among different acoustic emission events (cracks) by means of the identification of tensile, shear and mixed modes. The applications of DL in SHM systems is described by using the concept of Bidirectional Long Short Term Memory. We investigated on effective event descriptors to capture the unique characteristics from the different types of modes. Among them, Spectral Kurtosis and Spectral L2/L1 Norm exhibit distinctive behavior and effectively contributed to the learning process. This classification will contribute to unambiguously detect incipient damages, which is advantageous to realize predictive maintenance. Tests on experimental results confirm that this method achieves accurate classification (92%) capabilities of crack events and can impact on the design of future SHM technologies.

Are neural networks biased toward simple functions? Does depth always help learn more complex features? Is training the last layer of a network as good as training all layers? These questions seem unrelated at face value, but in this work we give all of them a common treatment from the spectral perspective. We will study the spectra of the *Conjugate Kernel*, CK, (also called the *Neural Network-Gaussian Process Kernel*), and the *Neural Tangent Kernel*, NTK. Roughly, the CK and the NTK tell us respectively "what a network looks like at initialization"and "what a network looks like during and after training." Their spectra then encode valuable information about the initial distribution and the training and generalization properties of neural networks. By analyzing the eigenvalues, we lend novel insights into the questions put forth at the beginning, and we verify these insights by extensive experiments of neural networks. We believe the computational tools we develop here for analyzing the spectra of CK and NTK serve as a solid foundation for future studies of deep neural networks. We have open-sourced the code for it and for generating the plots in this paper at github.com/thegregyang/NNspectra.