The increasing demand for democratizing machine learning algorithms for general software developers calls for hyperparameter optimization (HPO) solutions at low cost. Many machine learning algorithms have hyperparameters, which can cause a large variation in the training cost. But this effect is largely ignored in existing HPO methods, which are incapable to properly control cost during the optimization process. To address this problem, we develop a cost effective HPO solution. The core of our solution is a new randomized direct-search method. We prove a convergence rate of $O(\frac{\sqrt{d}}{\sqrt{K}})$ and provide an analysis on how it can be used to control evaluation cost under reasonable assumptions. Extensive evaluation using a latest AutoML benchmark shows a strong any time performance of the proposed HPO method when tuning cost-related hyperparameters.

Feature extraction for tensor data serves as an important step in many tasks such as anomaly detection, process monitoring, image classification, and quality control. Although many methods have been proposed for tensor feature extraction, there are still two challenges that need to be addressed: 1) how to reduce the computation cost for high dimensional and large volume tensor data; 2) how to interpret the output features and evaluate their significance. Although the most recent methods in deep learning, such as Convolutional Neural Network (CNN), have shown outstanding performance in analyzing tensor data, their wide adoption is still hindered by model complexity and lack of interpretability. To fill this research gap, we propose to use CP-decomposition to approximately compress the convolutional layer (CPAC-Conv layer) in deep learning. The contributions of our work could be summarized into three aspects: 1) we adapt CP-decomposition to compress convolutional kernels and derive the expressions of both forward and backward propagations for our proposed CPAC-Conv layer; 2) compared with the original convolutional layer, the proposed CPAC-Conv layer can reduce the number of parameters without decaying prediction performance. It can combine with other layers to build novel Neural Networks; 3) the value of decomposed kernels indicates the significance of the corresponding feature map, which increases model interpretability and provides us insights to guide feature selection.

Coronavirus disease (COVID-19) spread forecasting is an important task to track the growth of the pandemic. Existing predictions are merely based on qualitative analyses and mathematical modeling. The use of available big data with machine learning is still limited in COVID-19 growth prediction even though the availability of data is abundance. To make use of big data in the prediction using deep learning, we use long short-term memory (LSTM) method to learn the correlation of COVID-19 growth over time. The structure of an LSTM layer is searched heuristically until the best validation score is achieved. First, we trained training data containing confirmed cases from around the globe. We achieved favorable performance compared with that of the recurrent neural network (RNN) method with a comparable low validation error. The evaluation is conducted based on graph visualization and root mean squared error (RMSE). We found that it is not easy to achieve the same quantity of confirmed cases over time. However, LSTM provide a similar pattern between the actual cases and prediction. In the future, our proposed prediction can be used for anticipating forthcoming pandemics. The code is provided here: https://github.com/cbasemaster/lstmcorona

It feels like drones were built for this moment. The coronavirus pandemic has forced everyone to spend the majority of their time indoors and, where possible, maintain a healthy distance from anyone that doesn't live in the same building. Companies have introduced numerous measures to minimize the threat and spread of infection. Countless stores have acrylic screens, for instance, and many delivery drivers leave orders at your doorstep. But a robot -- or specifically, a drone -- offers a potentially safer and quicker method of exchanging goods and services. It's no wonder, then, that so many commercial UAV (unmanned aerial vehicle) operators are flourishing at the moment. In a time of crisis, they're keen to step forward and showcase the impact that drone deliveries can have on society.

Recently, a growing number of researchers have applied machine learning to assist users of interactive theorem provers. However, the expressive nature of underlying logics and esoteric structures of proof documents impede machine learning practitioners, who often do not have much expertise in formal logic, let alone Isabelle/HOL, from achieving a large scale success in this field. In this data description, we present a simple dataset that contains data on over 400k proof method applications along with over 100 extracted features for each in a format that can be processed easily without any knowledge about formal logic. Our simple data format allows machine learning practitioners to try machine learning tools to predict proof methods in Isabelle/HOL without requiring domain expertise in logic.

Wildfire modelling is an attempt to reproduce fire behaviour. Through active fire analysis, it is possible to reproduce a dynamical process, such as wildfires, with limited duration time series data. Recurrent neural networks (RNNs) can model dynamic temporal behaviour due to their ability to remember their internal input. In this paper, we compare the Gated Recurrent Unit (GRU) and the Long Short-Term Memory (LSTM) network. We try to determine whether a wildfire continues to burn and given that it does, we aim to predict which one of the 8 cardinal directions the wildfire will spread in. Overall the GRU performs better for longer time series than the LSTM. We have shown that although we are reasonable at predicting the direction in which the wildfire will spread, we are not able to asses if the wildfire continues to burn due to the lack of auxiliary data.

With 314 confirmed cases of the virus as of May 22, the East African country has enlisted the help of five anti-epidemic robots to battle the virus. The robots were donated by the United Nations Development Program (UNDP) to the Kanyinya treatment center that treats Covid-19 patients in the capital city, Kigali. The robots -- named Akazuba, Ikirezi, Mwiza, Ngabo, and Urumuri -- were received by the country's Minister of Health and Minister of ICT and Innovation last week. They will be used for mass temperature screening, monitoring patient status, and keeping medical records of Covid-19 patients, according to Rwanda's Ministry of ICT and Innovation. Keeping healthworkers safeThe robots perform a number of tasks relating to managing coronavirus.

Sickle cell disease (SCD) is a major public health priority throughout much of the world, affecting millions of people. In many regions, particularly those in resource-limited settings, SCD is not consistently diagnosed. In Africa, where the majority of SCD patients reside, more than 50% of the 0.2–0.3 million children born with SCD each year will die from it; many of these deaths are in fact preventable with correct diagnosis and treatment. Here, we present a deep learning framework which can perform automatic screening of sickle cells in blood smears using a smartphone microscope. This framework uses two distinct, complementary deep neural networks.

We construct embedded functional connectivity networks (FCN) from benchmark resting-state functional magnetic resonance imaging (rsfMRI) data acquired from patients with schizophrenia and healthy controls based on linear and nonlinear manifold learning algorithms, namely, Multidimensional Scaling (MDS), Isometric Feature Mapping (ISOMAP) and Diffusion Maps. Furthermore, based on key global graph-theoretical properties of the embedded FCN, we compare their classification potential using machine learning techniques. We also assess the performance of two metrics that are widely used for the construction of FCN from fMRI, namely the Euclidean distance and the lagged cross-correlation metric. We show that the FCN constructed with Diffusion Maps and the lagged cross-correlation metric outperform the other combinations.

It has been recognized that a heavily overparameterized artificial neural network exhibits surprisingly good generalization performance in various machine-learning tasks. Recent theoretical studies have made attempts to unveil the mystery of the overparameterization. In most of those previous works, the overparameterization is achieved by increasing the width of the network, while the effect of increasing the depth has been less well understood. In this work, we investigate the effect of increasing the depth within an overparameterized regime. To gain an insight into the advantage of depth, we introduce local and global labels as abstract but simple classification rules. It turns out that the locality of the relevant feature for a given classification rule plays an important role; our experimental results suggest that deeper is better for local labels, whereas shallower is better for global labels. We also compare the results of finite networks with those of the neural tangent kernel (NTK), which is equivalent to an infinitely wide network with a proper initialization and an infinitesimal learning rate. It is shown that the NTK does not correctly capture the depth dependence of the generalization performance, which indicates the importance of the feature learning, rather than the lazy learning.