Understanding dynamic fracture propagation is essential to predicting how brittle materials fail. Various mathematical models and computational applications have been developed to predict fracture evolution and coalescence, including finite-discrete element methods such as the Hybrid Optimization Software Suite (HOSS). While such methods achieve high fidelity results, they can be computationally prohibitive: a single simulation takes hours to run, and thousands of simulations are required for a statistically meaningful ensemble. We propose a machine learning approach that, once trained on data from HOSS simulations, can predict fracture growth statistics within seconds. Our method uses deep learning, exploiting the capabilities of a graph convolutional network to recognize features of the fracturing material, along with a recurrent neural network to model the evolution of these features. In this way, we simultaneously generate predictions for qualitatively distinct material properties. Our prediction for total damage in a coalesced fracture, at the final simulation time step, is within 3% of its actual value, and our prediction for total length of a coalesced fracture is within 2%. We also develop a novel form of data augmentation that compensates for the modest size of our training data, and an ensemble learning approach that enables us to predict when the material fails, with a mean absolute error of approximately 15%.

In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to train deep neural networks over several data sources. Our method allows for deep neural networks to be trained using data from multiple entities in a distributed fashion. We evaluate our algorithm on existing datasets and show that it obtains performance which is similar to a regular neural network trained on a single machine. We further extend it to incorporate semi-supervised learning when training with few labeled samples, and analyze any security concerns that may arise. Our algorithm paves the way for distributed training of deep neural networks in data sensitive applications when raw data may not be shared directly. Keywords: Multi Party Computation, Deep Learning, Distributed Systems 1. Introduction Deep neural networks have become the new state of the art in classification and prediction of high dimensional data such as images, videos and bio-sensors.

These sources contain images that viewers would have to interpret themselves. Most images do not have a description, but the human can largely understand them without their detailed captions. However, machine needs to interpret some form of image captions if humans need automatic image captions from it. Image captioning is important for many reasons. For example, they can be used for automatic image indexing. Image indexing is important for Content-Based Image Retrieval (CBIR) and therefore, it can be applied to many areas, including biomedicine, commerce, the military, education, digital libraries, and web searching. Social media platforms such as Facebook and Twitter can directly generate descriptions from images. The descriptions can include where we are (e.g., beach, cafe), what we wear and importantly what we are doing there.

Adversarial robustness has become an important research topic given empirical demonstrations on the lack of robustness of deep neural networks. Unfortunately, recent theoretical results suggest that adversarial training induces a strict tradeoff between classification accuracy and adversarial robustness. In this paper, we propose and then study a new regularization for any margin classifier or deep neural network. We motivate this regularization by a novel generalization bound that shows a tradeoff in classifier accuracy between maximizing its margin and average margin. We thus call our approach an average margin (AM) regularization, and it consists of a linear term added to the objective. We theoretically show that for certain distributions AM regularization can both improve classifier accuracy and robustness to adversarial attacks. We conclude by using both synthetic and real data to empirically show that AM regularization can strictly improve both accuracy and robustness for support vector machine's (SVM's) and deep neural networks, relative to unregularized classifiers and adversarially trained classifiers.

After the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However, deep learning is resource-intensive and the theory is not yet well developed. For small games, simple classical table-based Q-learning might still be the algorithm of choice. General Game Playing (GGP) provides a good testbed for reinforcement learning to research AGI. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee $\&$ Stone, IJCAI 2007) in GGP. In this paper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex)\footnote{source code: https://github.com/wh1992v/ggp-rl}, to allow comparison to Banerjee et al.. We find that Q-learning converges to a high win rate in GGP. For the $\epsilon$-greedy strategy, we propose a first enhancement, the dynamic $\epsilon$ algorithm. In addition, inspired by (Gelly $\&$ Silver, ICML 2007) we combine online search (Monte Carlo Search) to enhance offline learning, and propose QM-learning for GGP. Both enhancements improve the performance of classical Q-learning. In this work, GGP allows us to show, if augmented by appropriate enhancements, that classical table-based Q-learning can perform well in small games.

Dropout is a popular regularization technique in neural networks. Yet, the reason for its success is still not fully understood. This paper provides a new interpretation of Dropout from a frame theory perspective. This leads to a novel regularization technique for neural networks that minimizes the cross-correlation between filters in the network. We demonstrate its applicability in convolutional and fully connected layers in both feed-forward and recurrent networks.

The abundance of overlapping anatomical structures appearing in chest radiographs can reduce the performance of lung pathology detection by automated algorithms (CAD) as well as the human reader. In this paper, we present a deep learning based image processing technique for enhancing the contrast of soft lung structures in chest radiographs using Fully Convolutional Neural Networks (FCNN). Two 2D FCNN architectures were trained to accomplish the task: The first performs 2D lung segmentation which is used for normalization of the lung area. The second FCNN is trained to extract lung structures. To create the training images, we employed Simulated X-Ray or Digitally Reconstructed Radiographs (DRR) derived from 516 scans belonging to the LIDC-IDRI dataset. By first segmenting the lungs in the CT domain, we are able to create a dataset of 2D lung masks to be used for training the segmentation FCNN. For training the extraction FCNN, we create DRR images of only voxels belonging to the 3D lung segmentation which we call "Lung X-ray" and use them as target images. Once the lung structures are extracted, the original image can be enhanced by fusing the original input x-ray and the synthesized "Lung X-ray". We show that our enhancement technique is applicable to real x-ray data, and display our results on the recently released NIH Chest X-Ray-14 dataset. We see promising results when training a DenseNet-121 based architecture to work directly on the lung enhanced X-ray images.

The past few years have witnessed the flourishing of crowdsourced medical question answering (Q&A) websites. Patients who have medical information demands tend to post questions about their health conditions on these crowdsourced Q&A websites and get answers from other users. However, we observe that a large portion of new medical questions cannot be answered in time or receive only few answers from these websites. On the other hand, we notice that solved questions have great potential to solve this challenge. Motivated by these, we propose an end-to-end system that can automatically find similar questions for unsolved medical questions. By learning the vector presentation of unsolved questions and their candidate similar questions, the proposed system outputs similar questions according to the similarity between vector representations. Through the vector representation, the similar questions are found at the question level, and the diversity of medical questions expression issue can be addressed. Further, we handle two more important issues, i.e., training data generation issue and efficiency issue, associated with the LSTM training procedure and the retrieval of candidate similar questions. The effectiveness of the proposed system is validated on a large-scale real-world dataset collected from a crowdsourced maternal-infant Q&A website.

Despite wide adoption in the industry, our understanding of deep learning is still lagging. Theorists have long assumed networks with hundreds of thousands of neurons and orders of magnitude more individually weighted connections between them should suffer from a fundamental problem: over-parameterization [19] The spin glass model seems a great starting point for a very fertile research direction. Should we go down this path? First, the ultimate metric in machine learning is the generalisation accuracy rather than minimising the loss function, which only captures how well the model fits the training data [...] Second, it is known empirically that deeper minima have lower generalisation accuracy than shallower minima Before continuing our work on loss function topology, let's have a look at what is meant with flatness of minima. Consider the cartoon energy landscape (of the empirical loss function) in figure X discussed in [5].

Deep learning is all the rage these days, and is driving a surge in interest around artificial intelligence. However, despite the advantages that deep neural networks can bring for certain applications, the actual use cases for deep learning in the real world remain narrow, as traditional machine learning methods continue to lead the way. The rapid ascent of deep learning is arguably one of the least expected technological phenomena to have occurred in the past five years. While neural networks have been around for decades, it wasn't until the University of Toronto's Geoff Hinton paired those techniques with a new computational paradigm (GPU) and the availability of huge amounts of training data to yield what we now know as deep learning. The result is that deep neural network technology has evolved "at a lightening rate," Nvidia CEO Jenson Huang said earlier this year.