Identifying the physical aspect of the earth's surface (Land cover) as well as how we exploit the land (Land use) is a challenging problem in environment monitoring and many other subdomains. This can be done through field surveys or analyzing satellite images(Remote Sensing). While carrying out field surveys is more comprehensive and authoritative, it is an expensive project and mostly takes a long time to update. With recent developments in the Space industry and the increased availability of satellite images (both free and commercial), deep learning and Convolutional Neural Networks has shown a promising result in land use classification. In this project, I used the freely available Sentinel-2 satellite images to classify 9 land use classes and 24000 labeled images ( Figure 2).

Deep convolutional neural networks (CNNs) have achieved remarkable success in various fields. However, training an excellent CNN is practically a trial-and-error process that consumes a tremendous amount of time and computer resources. To accelerate the training process and reduce the number of trials, experts need to understand what has occurred in the training process and why the resulting CNN behaves as such. However, current popular training platforms, such as TensorFlow, only provide very little and general information, such as training/validation errors, which is far from enough to serve this purpose. To bridge this gap and help domain experts with their training tasks in a practical environment, we propose a visual analytics system, DeepTracker, to facilitate the exploration of the rich dynamics of CNN training processes and to identify the unusual patterns that are hidden behind the huge amount of training log. Specifically,we combine a hierarchical index mechanism and a set of hierarchical small multiples to help experts explore the entire training log from different levels of detail. We also introduce a novel cube-style visualization to reveal the complex correlations among multiple types of heterogeneous training data including neuron weights, validation images, and training iterations. Three case studies are conducted to demonstrate how DeepTracker provides its users with valuable knowledge in an industry-level CNN training process, namely in our case, training ResNet-50 on the ImageNet dataset. We show that our method can be easily applied to other state-of-the-art "very deep" CNN models.

Vortex induced vibrations of bluff bodies occur when the vortex shedding frequency is close to the natural frequency of the structure. Of interest is the prediction of the lift and drag forces on the structure given some limited and scattered information on the velocity field. This is an inverse problem that is not straightforward to solve using standard computational fluid dynamics (CFD) methods, especially since no information is provided for the pressure. An even greater challenge is to infer the lift and drag forces given some dye or smoke visualizations of the flow field. Here we employ deep neural networks that are extended to encode the incompressible Navier-Stokes equations coupled with the structure's dynamic motion equation. In the first case, given scattered data in space-time on the velocity field and the structure's motion, we use four coupled deep neural networks to infer very accurately the structural parameters, the entire time-dependent pressure field (with no prior training data), and reconstruct the velocity vector field and the structure's dynamic motion. In the second case, given scattered data in space-time on a concentration field only, we use five coupled deep neural networks to infer very accurately the vector velocity field and all other quantities of interest as before. This new paradigm of inference in fluid mechanics for coupled multi-physics problems enables velocity and pressure quantification from flow snapshots in small subdomains and can be exploited for flow control applications and also for system identification.

This paper proposes a non-parallel many-to-many voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE (ACVAE). The proposed method has three key features. First, it adopts fully convolutional architectures to construct the encoder and decoder networks so that the networks can learn conversion rules that capture time dependencies in the acoustic feature sequences of source and target speech. Second, it uses an information-theoretic regularization for the model training to ensure that the information in the attribute class label will not be lost in the conversion process. With regular CVAEs, the encoder and decoder are free to ignore the attribute class label input. This can be problematic since in such a situation, the attribute class label will have little effect on controlling the voice characteristics of input speech at test time. Such situations can be avoided by introducing an auxiliary classifier and training the encoder and decoder so that the attribute classes of the decoder outputs are correctly predicted by the classifier. Third, it avoids producing buzzy-sounding speech at test time by simply transplanting the spectral details of the input speech into its converted version. Subjective evaluation experiments revealed that this simple method worked reasonably well in a non-parallel many-to-many speaker identity conversion task.

Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural networks for text classification. Unlike the traditional dropout method in which the units are dropped randomly according to the same probability, we aim to use explicit instructions based on global information of the dataset to guide the training process. With GI-Dropout, the model is supposed to pay more attention to inapparent features or patterns. Experiments demonstrate the effectiveness of the dropout with global information on seven text classification tasks, including sentiment analysis and topic classification.

Deep learning (DL) is a form of machine learning that uses hierarchical layers of abstraction to model complex structures. DL requires efficient training strategies and these are at the heart of today's successful applications which range from natural language processing to engineering and financial analysis. While deep learning has been available for several decades there were only a few practical applications until the early 2010s when the field has changed for several reasons. The renaissance is due to a number of factors, in particular 1. Hardware and software for accelerated computing (GPUs and specialized linear algebra libraries) 2. Increased size of datasets (Massive Data) 3. Efficient algorithms algorithms, such as stochastic gradient descent (SGD). The goal of our article is to provide the reader with an overview of computational aspects underlying the algorithms and hardware, which allow modern deep learning models to be implemented at scale. Many of the leading Internet companies employ DL at scale Hazelwood et al. [2017]. The most impressive accomplishment of DL is its many successful applications in research and business.

Abstract--As opposed to manual feature engineering which is tedious and difficult to scale, network representation learning has attracted a surge of research interests as it automates the process of feature learning on graphs. The learned lowdimensional node vector representation is generalizable and eases the knowledge discovery process on graphs by enabling various off-the-shelf machine learning tools to be directly applied. Recent research has shown that the past decade of network embedding approaches either explicitly factorize a carefully designed matrix to obtain the low-dimensional node vector representation or are closely related to implicit matrix factorization, with the fundamental assumption that the factorized node connectivity matrix is low-rank. Nonetheless, the global low-rank assumption does not necessarily hold especially when the factorized matrix encodes complex node interactions, and the resultant single low-rank embedding matrix is insufficient to capture all the observed connectivity patterns. In this regard, we propose a novel multilevel network embedding framework BoostNE, which can learn multiple network embedding representations of different granularity from coarse to fine without imposing the prevalent global low-rank assumption. The proposed BoostNE method is also in line with the successful gradient boosting method in ensemble learning as multiple weak embeddings lead to a stronger and more effective one. We assess the effectiveness of the proposed BoostNE framework by comparing it with existing state-of-the-art network embedding methods on various datasets, and the experimental results corroborate the superiority of the proposed BoostNE network embedding framework. Learning meaningful and discriminative representations of nodes in a network is essential for various network analytical tasks as it avoids the laborious manual feature engineering process.

The model size of deep neural network is getting larger and larger to realize superior performance in complicated tasks. This makes it difficult to implement deep neural network in small edge-computing devices. To overcome this problem, model compression methods have been gathering much attention. However, there have been only few theoretical back-grounds that explain what kind of quantity determines the compression ability. To resolve this issue, we develop a new theoretical frame-work for model compression, and propose a new method called {\it Spectral-Pruning} based on the theory. Our theoretical analysis is based on the observation such that the eigenvalues of the covariance matrix of the output from nodes in the internal layers often shows rapid decay. We define "degree of freedom" to quantify an intrinsic dimensionality of the model by using the eigenvalue distribution and show that the compression ability is essentially controlled by this quantity. Along with this, we give a generalization error bound of the compressed model. Our proposed method is applicable to wide range of models, unlike the existing methods, e.g., ones possess complicated branches as implemented in SegNet and ResNet. Our method makes use of both "input" and "output" in each layer and is easy to implement. We apply our method to several datasets to justify our theoretical analyses and show that the proposed method achieves the state-of-the-art performance.

Numerous studies have investigated the effectiveness of neural network quantization on pattern classification tasks. The present study, for the first time, investigated the performance of speech enhancement (a regression task in speech processing) using a novel exponent-only floating-point quantized neural network (EOFP-QNN). The proposed EOFP-QNN consists of two stages: mantissa-quantization and exponent-quantization. In the mantissa-quantization stage, EOFP-QNN learns how to quantize the mantissa bits of the model parameters while preserving the regression accuracy using the least mantissa precision. In the exponent-quantization stage, the exponent part of the parameters is further quantized without causing any additional performance degradation. We evaluated the proposed EOFP quantization technique on two types of neural networks, namely, bidirectional long short-term memory (BLSTM) and fully convolutional neural network (FCN), on a speech enhancement task. Experimental results showed that the model sizes can be significantly reduced (the model sizes of the quantized BLSTM and FCN models were only 18.75% and 21.89%, respectively, compared to those of the original models) while maintaining satisfactory speech-enhancement performance.

Most of the Neural Machine Translation (NMT) models are based on the sequence-to-sequence (Seq2Seq) model with an encoder-decoder framework equipped with the attention mechanism. However, the conventional attention mechanism treats the decoding at each time step equally with the same matrix, which is problematic since the softness of the attention for different types of words (e.g. content words and function words) should differ. Therefore, we propose a new model with a mechanism called Self-Adaptive Control of Temperature (SACT) to control the softness of attention by means of an attention temperature. Experimental results on the Chinese-English translation and English-Vietnamese translation demonstrate that our model outperforms the baseline models, and the analysis and the case study show that our model can attend to the most relevant elements in the source-side contexts and generate the translation of high quality.