Experimental corn hybrids are created in plant breeding programs by crossing two parents, so-called inbred and tester, together. Identification of best parent combinations for crossing is challenging since the total number of possible cross combinations of parents is large and it is impractical to test all possible cross combinations due to limited resources of time and budget. In the 2020 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the historical yield performances of around 4% of total cross combinations of 593 inbreds with 496 testers which were planted in 280 locations between 2016 and 2018 and asked participants to predict the yield performance of cross combinations of inbreds and testers that have not been planted based on the historical yield data collected from crossing other inbreds and testers. In this paper, we present a collaborative filtering method which is an ensemble of matrix factorization method and neural networks to solve this problem. Our computational results suggested that the proposed model significantly outperformed other models such as LASSO, random forest (RF), and neural networks. Presented method and results were produced within the 2020 Syngenta Crop Challenge.

In few-shot classification, the aim is to learn models able to discriminate classes with only a small number of labelled examples. Most of the literature considers the problem of labelling a single unknown input at a time. Instead, it can be beneficial to consider a setting where a batch of unlabelled inputs are treated conjointly and non-independently. In this paper, we propose a method able to exploit three levels of information: a) feature extractors pretrained on generic datasets, b) few labelled examples of classes to discriminate and c) other available unlabelled inputs. If for a), we use state-of-the-art approaches, we introduce the use of simplified graph convolutions to perform b) and c) together. Our proposed model reaches state-of-the-art accuracy with a $6-11\%$ increase compared to available alternatives on standard few-shot vision classification datasets.

Since DeepMind's AlphaZero, Zero learning quickly became the state-of-the-art method for many board games. It can be improved using a fully convolutional structure (no fully connected layer). Using such an architecture plus global pooling, we can create bots independent of the board size. The training can be made more robust by keeping track of the best checkpoints during the training and by training against them. Using these features, we release Polygames, our framework for Zero learning, with its library of games and its checkpoints. We won against strong humans at the game of Hex in 19x19, which was often said to be untractable for zero learning; and in Havannah. We also won several first places at the TAAI competitions.

Published in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 2019DP-CGAN: Differentially Private Synthetic Data and Label Generation Reihaneh Torkzadehmahani University of California, Santa Cruz rtorkzad@ucsc.edu January 28, 2020 Abstract Generative Adversarial Networks (GANs) are one of the well-known models to generate synthetic data including images, especially for research communities that cannot use original sensitive datasets because they are not publicly accessible. One of the main challenges in this area is to preserve the privacy of individuals who participate in the training of the GAN models. To address this challenge, we introduce a Differentially Private Conditional GAN (DP-CGAN) training framework based on a new clipping and perturbation strategy, which improves the performance of the model while preserving privacy of the training dataset. DP-CGAN generates both synthetic data and corresponding labels and leverages the recently introduced R enyi differential privacy accountant to track the spent privacy budget. The experimental results show that DP-CGAN can generate visually and empirically promising results on the MNIST dataset with a single-digit epsilon parameter in differential privacy. 1 Introduction Recent studies have shown that deep neural networks (DNNs) can achieve state-of-the-art performance in various applications such as image recognition [1, 2], natural language processing [3], speech recognition [4, 5] and complex video games [6, 7].

Convolutional neural networks have had a great success in numerous tasks, including image classification, object detection, sequence modelling, and many more. It is generally assumed that such neural networks are translation invariant, meaning that they can detect a given feature independent of its location in the input image. While this is true for simple cases, where networks are composed of a restricted number of layer classes and where images are fairly simple, complex images with common state-of-the-art networks do not usually enjoy this property as one might hope. This paper shows that most of the existing convolutional architectures define, at initialisation, a specific feature importance landscape that conditions their capacity to attend to different locations of the images later during training or even at test time. We demonstrate how this phenomenon occurs under specific conditions and how it can be adjusted under some assumptions. We derive the P-objective, or PILCRO for Pixel-wise Importance Landscape Curvature Regularised Objective, a simple regularisation technique that favours weight configurations that produce smooth, low-curvature importance landscapes that are conditioned on the data and not on the chosen architecture. Through extensive experiments, we further show that P-regularised versions of popular computer vision networks have a flat importance landscape, train faster, result in a better accuracy and are more robust to noise at test time, when compared to their original counterparts in common computer-vision classification settings.

In recent years, the growth of Internet of Things (IoT) as an emerging technology has been unbelievable. The number of networkenabled devices in IoT domains is increasing dramatically, leading to the massive production of electronic data. These data contain valuable information which can be used in various areas, such as science, industry, business and even social life. To extract and analyze this information and make IoT systems smart, the only choice is entering artificial intelligence (AI) world and leveraging the power of machine learning and deep learning techniques. This paper evaluates the performance of 11 popular machine and deep learning algorithms for classification task using six IoT-related datasets. These algorithms are compared according to several performance evaluation metrics including precision, recall, f1-score, accuracy, execution time, ROC-AUC score and confusion matrix. A specific experiment is also conducted to assess the convergence speed of developed models. The comprehensive experiments indicated that, considering all performance metrics, Random Forests performed better than other machine learning models, while among deep learning models, ANN and CNN achieved more interesting results.

Earth's physical properties like atmosphere, topography and ground instability can be determined by differencing billions of phase measurements (pixels) in subsequent matching Interferometric Synthetic Aperture Radar (InSAR) images. Quality (coherence) of each pixel can vary from perfect information (1) to complete noise (0), which needs to be quantified, alongside filtering information-bearing pixels. Phase filtering is thus critical to InSAR's Digital Elevation Model (DEM) production pipeline, as it removes spatial inconsistencies (residues), immensely improving the subsequent unwrapping. Recent explosion in quantity of available InSAR data can facilitate Wide Area Monitoring (WAM) over several geographical regions, if effective and efficient automated processing can obviate manual quality-control. Advances in parallel computing architectures and Convolutional Neural Networks (CNNs) which thrive on them to rival human performance on visual pattern recognition makes this approach ideal for InSAR phase filtering for WAM, but remains largely unexplored. We propose "GenInSAR", a CNN-based generative model for joint phase filtering and coherence estimation. We use satellite and simulated InSAR images to show overall superior performance of GenInSAR over five algorithms qualitatively, and quantitatively using Phase and Coherence Root-Mean-Squared-Error, Residue Reduction Percentage, and Phase Cosine Error.

A BSTRACT V ariance reduction methods such as SVRG (Johnson & Zhang, 2013) and SpiderBoost (Wang et al., 2018) use a mixture of large and small batch gradients to reduce the variance of stochastic gradients. Compared to SGD (Robbins & Monro, 1951), these methods require at least double the number of operations per update to model parameters. To reduce the computational cost of these methods, we introduce a new sparsity operator: The random-top- k operator. Our operator reduces computational complexity by estimating gradient sparsity exhibited in a variety of applications by combining the top-k operator (Stich et al., 2018; Aji & Heafield, 2017) and the randomized coordinate descent operator. With this operator, large batch gradients offer an extra benefit beyond variance reduction: A reliable estimate of gradient sparsity. Theoretically, our algorithm is at least as good as the best algorithm (SpiderBoost), and further excels in performance whenever the random-top- k operator captures gradient sparsity. Empirically, our algorithm consistently outperforms SpiderBoost using various models on various tasks including image classification, natural language processing, and sparse matrix factorization. We also provide empirical evidence to support the intuition behind our algorithm via a simple gradient entropy computation, which serves to quantify gradient sparsity at every iteration. It updates the iterate x with x η f I(x), where η is the learning rate and f I(x) is the batch stochastic gradient, i.e. f I(x) 1 I null i I f i(x).

Artificial intelligence (AI) has been a topic of major research for many years. Especially, with the emergence of deep neural network (DNN), these studies have been tremendously successful. Today machines are capable of making faster, more accurate decision than human. Thanks to the great development of machine learning (ML) techniques, ML have been used many different fields such as education, medicine, malware detection, autonomous car etc. In spite of having this degree of interest and much successful research, ML models are still vulnerable to adversarial attacks. Attackers can manipulate clean data in order to fool the ML classifiers to achieve their desire target. For instance; a benign sample can be modified as a malicious sample or a malicious one can be altered as benign while this modification can not be recognized by human observer. This can lead to many financial losses, or serious injuries, even deaths. The motivation behind this paper is that we emphasize this issue and want to raise awareness. Therefore, the security gap of mammographic image classifier against adversarial attack is demonstrated. We use mamographic images to train our model then evaluate our model performance in terms of accuracy. Later on, we poison original dataset and generate adversarial samples that missclassified by the model. We then using structural similarity index (SSIM) analyze similarity between clean images and adversarial images. Finally, we show how successful we are to misuse by using different poisoning factors.

With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue. In recent years, we have observed a new desideratum of considering long-term rewards of multiple related recommendation tasks simultaneously. The consideration of long-term rewards is strongly tied to business revenue and growth. Learning multiple tasks simultaneously could generally improve the performance of individual task due to knowledge sharing in multi-task learning. While a few existing works have studied long-term rewards in recommendations, they mainly focus on a single recommendation task. In this paper, we propose {\it PoDiRe}: a \underline{po}licy \underline{di}stilled \underline{re}commender that can address long-term rewards of recommendations and simultaneously handle multiple recommendation tasks. This novel recommendation solution is based on a marriage of deep reinforcement learning and knowledge distillation techniques, which is able to establish knowledge sharing among different tasks and reduce the size of a learning model. The resulting model is expected to attain better performance and lower response latency for real-time recommendation services. In collaboration with Samsung Game Launcher, one of the world's largest commercial mobile game platforms, we conduct a comprehensive experimental study on large-scale real data with hundreds of millions of events and show that our solution outperforms many state-of-the-art methods in terms of several standard evaluation metrics.