Operational medical environments require reliable hands-free solutions to extract data from audio captured under noisy scenarios during rescue missions and provide timely information. However, approaches using automatic speech recognition (ASR) and natural language processing (NLP) techniques are complex as these conversations have a wide range of noise, involve medical terms from multiple speakers, and occur in high-stress environments, among others. These are further complicated by the lack of large training datasets for operational medical scenarios. To address these issues, we developed a platform that enables resilient hands-free data collection, preserves complete documentation through stages of care, and presents the information in near real-time, critical for the medical operation. Our work uniquely focused on systematic evaluation and improvement of a deep neural network-based ASR system by leveraging realistic testing data obtained from medical simulations of battlefield scenarios, which to our knowledge have not been addressed in any prior work. The system performance is shown to improve significantly using multi-style training, language model adaptation for the medical domain, speech enhancement, and NLP techniques.

The main challenge of adapting Graph convolutional networks (GCNs) to large-scale graphs is the scalability issue due to the uncontrollable neighborhood expansion in the aggregation stage. Several sampling algorithms have been proposed to limit the neighborhood expansion. However, these algorithms focus on minimizing the variance in sampling to approximate the original aggregation. This leads to two critical problems: 1) low accuracy because the sampling policy is agnostic to the performance of the target task, and 2) vulnerability to noise or adversarial attacks on the graph.

Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in generative modeling of novel chemical structures. However, current generative approaches exhibit a significant challenge: they do not ensure that the proposed molecular structures can be feasibly synthesized nor do they provide the synthesis routes of the proposed small molecules, thereby seriously limiting their practical applicability. In this work, we propose a novel reinforcement learning (RL) setup for de novo drug design: Policy Gradient for Forward Synthesis (PGFS), that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo drug design system. In this setup, the agent learns to navigate through the immense synthetically accessible chemical space by subjecting initial commercially available molecules to valid chemical reactions at every time step of the iterative virtual synthesis process. The proposed environment for drug discovery provides a highly challenging test-bed for RL algorithms owing to the large state space and high-dimensional continuous action space with hierarchical actions. PGFS achieves state-of-the-art performance in generating structures with high QED and clogP. Moreover, we validate PGFS in an in-silico proof-of-concept associated with three HIV targets. Finally, we describe how the end-to-end training conceptualized in this study represents an important paradigm in radically expanding the synthesizable chemical space and automating the drug discovery process.

Speech enhancement is an essential component in robust automatic speech recognition (ASR) systems. Most speech enhancement methods are nowadays based on neural networks that use feature-mapping or mask-learning. This paper proposes a novel speech enhancement method that integrates time-domain feature mapping and mask learning into a unified framework using a Generative Adversarial Network (GAN). The proposed framework processes the received waveform and decouples speech and noise signals, which are fed into two short-time Fourier transform (STFT) convolution 1-D layers that map the waveforms to spectrograms in the complex domain. These speech and noise spectrograms are then used to compute the speech mask loss. The proposed method is evaluated using the TIMIT data set for seen and unseen signal-to-noise ratio conditions. It is shown that the proposed method outperforms the speech enhancement methods that use Deep Neural Network (DNN) based speech enhancement or a Speech Enhancement Generative Adversarial Network (SEGAN).

We present a novel graph-neural-network-based system to effectively represent large-scale 3D point clouds with the applications to autonomous driving. Many previous works studied the representations of 3D point clouds based on two approaches, voxelization, which causes discretization errors and learning, which is hard to capture huge variations in large-scale scenarios. In this work, we combine voxelization and learning: we discretize the 3D space into voxels and propose novel graph inception networks to represent 3D points in each voxel. This combination makes the system avoid discretization errors and work for large-scale scenarios. The entire system for large-scale 3D point clouds acts like the blocked discrete cosine transform for 2D images; we thus call it the point cloud neural transform (PCT). We further apply the proposed PCT to represent real-time LiDAR sweeps produced by self-driving cars and the PCT with graph inception networks significantly outperforms its competitors.

In this paper, we introduce a generalized value iteration network (GVIN), which is an end-to-end neural network planning module. GVIN emulates the value iteration algorithm by using a novel graph convolution operator, which enables GVIN to learn and plan on irregular spatial graphs. We propose three novel differentiable kernels as graph convolution operators and show that the embedding-based kernel achieves the best performance. Furthermore, we present episodic Q-learning, an improvement upon traditional n-step Q-learning that stabilizes training for VIN and GVIN. Lastly, we evaluate GVIN on planning problems in 2D mazes, irregular graphs, and real-world street networks, showing that GVIN generalizes well for both arbitrary graphs and unseen graphs of larger scaleand outperforms a naive generalization of VIN (discretizing a spatial graph into a 2D image).

High density oligonucleotide array (microarray) from Affymetrix has been widely used for the measurements of gene expressions. Currently, public data repositories, such as Gene Expression Omnibus (GEO) of the National Center for Biotechnology Information (NCBI), have accumulated large amounts of microarray data. Efficient integrative analysis of those microarray data will provide significant knowledge about biological systems. None of the existing microarray preprocessing and quality assessment tools can handle very large microarray datasets with tens of thousands of experiments. The preprocessing and quality assessment of microarray datasets contain both data-intensive and compute-intensive tasks. In this paper, we develop a new set of tools using a mix of the Hadoop (for data intensive tasks) and the General-Purpose Graphics Processing Units (GPGPUs) (for compute intensive tasks) to efficiently process large microarray data. Evaluation of our new tools on large microarray datasets with ten thousands of experiments showed promising superior performance. We demonstrate that the combination of Hadoop and GPGPU computation is effective for complex scientific applications that contain both data-intensive and compute-intensive tasks. Our new tool set will make it possible to utilize valuable large microarray data in the public repositories.