PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1902.06226

Robust Sub-meter Level Indoor Localization - A Logistic Regression Approach

Indoor localization becomes a raising demand in our daily lives. Due to the massive deployment in the indoor environment nowadays, WiFi systems have been applied to high accurate localization recently. Although the traditional model based localization scheme can achieve sub-meter level accuracy by fusing multiple channel state information (CSI) observations, the corresponding computational overhead is significant. To address this issue, the model-free localization approach using deep learning framework has been proposed and the classification based technique is applied. In this paper, instead of using classification based mechanism, we propose to use a logistic regression based scheme under the deep learning framework, which is able to achieve sub-meter level accuracy (97.2cm medium distance error) in the standard laboratory environment and maintain reasonable online prediction overhead under the single WiFi AP settings. We hope the proposed logistic regression based scheme can shed some light on the model-free localization technique and pave the way for the practical deployment of deep learning based WiFi localization systems.

arXiv:1902.02647

Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?

This work deals with the use of emerging deep learning techniques in future wireless communication networks. It will be shown that data-driven approaches should not replace, but rather complement traditional design techniques based on mathematical models. Extensive motivation is given for why deep learning based on artificial neural networks will be an indispensable tool for the design and operation of future wireless communications networks, and our vision of how artificial neural networks should be integrated into the architecture of future wireless communication networks is presented. A thorough description of deep learning methodologies is provided, starting with the general machine learning paradigm, followed by a more in-depth discussion about deep learning and artificial neural networks, covering the most widely-used artificial neural network architectures and their training methods. Deep learning will also be connected to other major learning frameworks such as reinforcement learning and transfer learning. A thorough survey of the literature on deep learning for wireless communication networks is provided, followed by a detailed description of several novel case-studies wherein the use of deep learning proves extremely useful for network design. For each case-study, it will be shown how the use of (even approximate) mathematical models can significantly reduce the amount of live data that needs to be acquired/measured to implement data-driven approaches. For each application, the merits of the proposed approaches will be demonstrated by a numerical analysis in which the implementation and training of the artificial neural network used to solve the problem is discussed. Finally, concluding remarks describe those that in our opinion are the major directions for future research in this field.

arXiv:1901.06537

Deep-Learning-based Millimeter-Wave Massive MIMO for Hybrid Precoding

Millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) has been regarded to be an emerging solution for the next generation of communications, in which hybrid analog and digital precoding is an important method for reducing the hardware complexity and energy consumption associated with mixed signal components. However, the fundamental limitations of the existing hybrid precoding schemes is that they have high computational complexity and fail to fully exploit the spatial information. To overcome these limitations, this paper proposes, a deep-learning-enabled mmWave massive MIMO framework for effective hybrid precoding, in which each selection of the precoders for obtaining the optimized decoder is regarded as a mapping relation in the deep neural network (DNN). Specifically, the hybrid precoder is selected through training based on the DNN for optimizing precoding process of the mmWave massive MIMO. Additionally, we present extensive simulation results to validate the excellent performance of the proposed scheme. The results exhibit that the DNN-based approach is capable ofminimizing the bit error ratio (BER) and enhancing spectrum efficiency of the mmWave massive MIMO, which achieves better performance in hybrid precoding compared with conventional schemes while substantially reducing the required computational complexity.

arXiv:1901.02005

Deep Learning Assisted Antenna Selection in Untrusted Relay Networks

This letter mainly studies the transmit antenna selection(TAS) based on deep learning (DL) scheme in untrusted relay networks. In previous work, we discover that machine learning (ML)-based antenna selection schemes have small performance degradation caused by complicated coupling relationship between achievable secrecy rate and the channel gains. To solve the issue, we here introduce deep neural network (DNN) to decouple the complicated relationship. The simulation results show the DNN scheme can achieve better decoupling and thus perform almost the same performance with conventional exhausted searching scheme.

arXiv:1812.00023

Cascade-Net: a New Deep Learning Architecture for OFDM Detection

In this paper, we consider using deep neural network for OFDM symbol detection and demonstrate its performance advantages in combating large Doppler Shift. In particular, a new architecture named Cascade-Net is proposed for detection, where deep neural network is cascading with a zero-forcing preprocessor to prevent the network stucking in a saddle point or a local minimum point. In addition, we propose a sliding detection approach in order to detect OFDM symbols with large number of subcarriers. We evaluate this new architecture, as well as the sliding algorithm, using the Rayleigh channel with large Doppler spread, which could degrade detection performance in an OFDM system and is especially severe for high frequency band and mmWave communications. The numerical results of OFDM detection in SISO scenario show that cascade-net can achieve better performance than zero-forcing method while providing robustness against ill conditioned channels. We also show the better performance of the sliding cascade network (SCN) compared to sliding zero-forcing detector through numerical simulation.

arXiv:1811.11249

A Deep Learning Strategy for Vehicular Floating Content Management

Floating Content (FC) is a communication paradigm for the local dissemination of contextualized information through D2D connectivity, in a way which minimizes the use of resources while achieving some specified performance target. Existing approaches to FC dimensioning are based on unrealistic system assumptions that make them, highly inaccurate and overly conservative when applied in realistic settings. In this paper, we present a first step towards the development of a cognitive approach to efficient dynamic management of FC. We propose a deep learning strategy for FC dimensioning, which exploits a Convolutional Neural Network(CNN) to efficiently modulate over time the resources employed by FC in a QoS-aware manner. Numerical evaluations show that our approach achieves a maximum rejection rate of3%, and resource savings of 37.5% with respect to the benchmark strategy

arXiv:1811.04521

Deep Learning Based Transmitter Identification using Power Amplifier Nonlinearity

The imperfections in the RF frontend of different transmitters can be used to distinguish them. This process is called transmitter identification using RF fingerprints. The nonlinearity in the power amplifier of the RF frontend is a significant cause of the discrepancy in RF fingerprints, which enables transmitter identification. In this work, we use deep learning to identify different transmitters using their nonlinear characteristics. By developing a nonlinear model generator based on extensive measurements, we were able to extend the evaluation of transmitter identification to include a larger number of transmitters beyond what exists in the literature. We were also able to study the impact of transmitter variability on identification accuracy. Additionally, many other factors were considered including modulation type, length of data used for identification, and type of data being transmitted whether identical or random under a realistic channel model. Simulation results were compared with experiments which confirmed similar trends.

arXiv:1811.02668

Automated Diagnosis of Lymphoma with Digital Pathology Images Using Deep Learning

Recent studies have shown promising results in using Deep Learning to detect malignancy in whole slide imaging. However, they were limited to just predicting positive or negative finding for a specific neoplasm. We attempted to use Deep Learning with a convolutional neural network algorithm to build a lymphoma diagnostic model for four diagnostic categories: benign lymph node, diffuse large B cell lymphoma, Burkitt lymphoma, and small lymphocytic lymphoma. Our software was written in Python language. We obtained digital whole slide images of Hematoxylin and Eosin stained slides of 128 cases including 32 cases for each diagnostic category. Four sets of 5 representative images, 40x40 pixels in dimension, were taken for each case. A total of 2,560 images were obtained from which 1,856 were used for training, 464 for validation and 240 for testing. For each test set of 5 images, the predicted diagnosis was combined from prediction of 5 images. The test results showed excellent diagnostic accuracy at 95% for image-by-image prediction and at 10% for set-by-set prediction. This preliminary study provided a proof of concept for incorporating automated lymphoma diagnostic screen into future pathology workflow to augment the pathologists' productivity.

arXiv:1811.00882

Learning to decompose the modes in few-mode fibers with deep convolutional neural network

We introduce deep learning technique to perform complete mode decomposition for few-mode optical fiber for the first time. Our goal is to learn a fast and accurate mapping from near-field beam profiles to the complete mode coefficients, including both modal amplitudes and phases. We train the convolutional neural network with simulated beam patterns, and evaluate the network on both of the simulated beam data and the real beam data. In simulated beam data testing, the correlation between the reconstructed and the ideal beam profiles can achieve 0.9993 and 0.995 for 3-mode case and 5-mode case respectively. While in the real 3-mode beam data testing, the average correlation is 0.9912 and the mode decomposition can be potentially performed at 33 Hz frequency on Graphic Processing Unit, indicating real-time processing ability. The quantitative evaluations demonstrate the superiority of our deep learning based approach.

arXiv:1811.00334

Deep Learning for Tube Amplifier Emulation

Analog audio effects and synthesizers often owe their distinct sound to circuit nonlinearities. Faithfully modeling such significant aspect of the original sound in virtual analog software can prove challenging. The current work proposes a generic data-driven approach to virtual analog modeling and applies it to the Fender Bassman 56F-A vacuum-tube amplifier. Specifically, a feedforward variant of the WaveNet deep neural network is trained to carry out a regression on audio waveform samples from input to output of a SPICE model of the tube amplifier. The output signals are pre-emphasized to assist the model at learning the high-frequency content. The results of a listening test suggest that the proposed model accurately emulates the reference device. In particular, the model responds to user control changes, and faithfully restitutes the range of sonic characteristics found across the configurations of the original device.

arXiv:1810.12097

Ruuh: A Deep Learning Based Conversational Social Agent

Dialogue systems and conversational agents are becoming increasingly popular in the modern society but building an agent capable of holding intelligent conversation with its users is a challenging problem for artificial intelligence. In this demo, we demonstrate a deep learning based conversational social agent called "Ruuh" (facebook.com/Ruuh) designed by a team at Microsoft India to converse on a wide range of topics. Ruuh needs to think beyond the utilitarian notion of merely generating "relevant" responses and meet a wider range of user social needs, like expressing happiness when user's favorite team wins, sharing a cute comment on showing the pictures of the user's pet and so on. The agent also needs to detect and respond to abusive language, sensitive topics and trolling behavior of the users. Many of these problems pose significant research challenges which will be demonstrated in our demo. Our agent has interacted with over 2 million real world users till date which has generated over 150 million user conversations.

arXiv:1810.11367

LAMVI-2: A Visual Tool for Comparing and Tuning Word Embedding Models

Tuning machine learning models, particularly deep learning architectures, is a complex process. Automated hyperparameter tuning algorithms often depend on specific optimization metrics. However, in many situations, a developer trades one metric against another: accuracy versus overfitting, precision versus recall, smaller models and accuracy, etc. With deep learning, not only are the model's representations opaque, the model's behavior when parameters "knobs" are changed may also be unpredictable. Thus, picking the "best" model often requires time-consuming model comparison. In this work, we introduce LAMVI-2, a visual analytics system to support a developer in comparing hyperparameter settings and outcomes. By focusing on word-embedding models ("deep learning for text") we integrate views to compare both high-level statistics as well as internal model behaviors (e.g., comparing word 'distances'). We demonstrate how developers can work with LAMVI-2 to more quickly and accurately narrow down an appropriate and effective application-specific model.

arXiv:1810.10337

Projecting Trouble: Light Based Adversarial Attacks on Deep Learning Classifiers

This work demonstrates a physical attack on a deep learning image classification system using projected light onto a physical scene. Prior work is dominated by techniques for creating adversarial examples which directly manipulate the digital input of the classifier. Such an attack is limited to scenarios where the adversary can directly update the inputs to the classifier. This could happen by intercepting and modifying the inputs to an online API such as Clarifai or Cloud Vision. Such limitations have led to a vein of research around physical attacks where objects are constructed to be inherently adversarial or adversarial modifications are added to cause misclassification. Our work differs from other physical attacks in that we can cause misclassification dynamically without altering physical objects in a permanent way. We construct an experimental setup which includes a light projection source, an object for classification, and a camera to capture the scene. Experiments are conducted against 2D and 3D objects from CIFAR-10. Initial tests show projected light patterns selected via differential evolution could degrade classification from 98% to 22% and 89% to 43% probability for 2D and 3D targets respectively. Subsequent experiments explore sensitivity to physical setup and compare two additional baseline conditions for all 10 CIFAR classes. Some physical targets are more susceptible to perturbation. Simple attacks show near equivalent success, and 6 of the 10 classes were disrupted by light.

arXiv:1810.10323

Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments

Object detection in streaming images is a major step in different detection-based applications, such as object tracking, action recognition, robot navigation, and visual surveillance applications. In mostcases, image quality is noisy and biased, and as a result, the data distributions are disturbed and imbalanced. Most object detection approaches, such as the faster region-based convolutional neural network (Faster RCNN), Single Shot Multibox Detector with 300x300 inputs (SSD300), and You Only Look Once version 2 (YOLOv2), rely on simple sampling without considering distortions and noise under real-world changing environments, despite poor object labeling. In this paper, we propose an Incremental active semi-supervised learning (IASSL) technology for unseen object detection. It combines batch-based active learning (AL) and bin-based semi-supervised learning (SSL) to leverage the strong points of AL's exploration and SSL's exploitation capabilities. A collaborative sampling method is also adopted to measure the uncertainty and diversity of AL and the confidence in SSL. Batch-based AL allows us to select more informative, confident, and representative samples with low cost. Bin-based SSL divides streaming image samples into several bins, and each bin repeatedly transfers the discriminative knowledge of convolutional neural network (CNN) deep learning to the next bin until the performance criterion is reached. IASSL can overcome noisy and biased labels in unknown, cluttered data distributions. We obtain superior performance, compared to state-of-the-art technologies such as Faster RCNN, SSD300, and YOLOv2.

arXiv:1810.09958

ISA Mapper: A Compute and Hardware Agnostic Deep Learning Compiler

Domain specific accelerators present new challenges and opportunities for code generation onto novel instruction sets, communication fabrics, and memory architectures. In this paper we introduce an intermediate representation (IR) which enables both deep learning computational kernels and hardware capabilities to be described in the same IR. We then formulate and apply instruction mapping to determine the possible ways a computation can be performed on a hardware system. Next, our scheduler chooses a specific mapping and determines the data movement and computation order. In order to manage the large search space of mappings and schedules, we developed a flexible framework that allows heuristics, cost models, and potentially machine learning to facilitate this search problem. With this system, we demonstrate the automated extraction of matrix multiplication kernels out of recent deep learning kernels such as depthwise-separable convolution. In addition, we demonstrate two to five times better performance on DeepBench sized GEMMs and GRU RNN execution when compared to state-of-the-art (SOTA) implementations on new hardware and up to 85% of the performance for SOTA implementations on existing hardware.

arXiv:1810.08906

Analog-to-digital conversion revolutionized by deep learning

As the bridge between the analog world and digital computers, analog-to-digital converters are generally used in modern information systems such as radar, surveillance, and communications. For the configuration of analog-to-digital converters in future high-frequency broadband systems, we introduce a revolutionary architecture that adopts deep learning technology to overcome tradeoffs between bandwidth, sampling rate, and accuracy. A photonic front-end provides broadband capability for direct sampling and speed multiplication. Trained deep neural networks learn the patterns of system defects, maintaining high accuracy of quantized data in a succinct and adaptive manner. Based on numerical and experimental demonstrations, we show that the proposed architecture outperforms state-of-the-art analog-to-digital converters, confirming the potential of our approach in future analog-to-digital converter design and performance enhancement of future information systems.

arXiv:1809.04768

Deep Learning for Waveform Estimation and Imaging in Passive Radar

We consider a bistatic configuration with a stationary transmitter transmitting unknown waveforms of opportunity and a moving receiver, and present a Deep Learning (DL) framework for passive synthetic aperture radar (SAR) imaging. Existing passive radar methods require two or more antennas which are either spatially separated or colocated with sufficient directivity to estimate the underlying waveform prior to imaging. Our approach to passive radar only requires a single receiver, hence reduces cost and increases versatility. We approach DL from an optimization perspective and formulate image reconstruction as a machine learning task. By unfolding the iterations of a proximal gradient descent algorithm, we construct a deep recurrent neural network (RNN) that is parameterized by transmitted waveforms. We cascade the RNN structure with a decoder stage to form a recurrent-auto encoder architecture. We then utilize backpropagation to learn transmitted waveforms by training the network in an unsupervised manner using SAR measurements. The highly non-convex problem of backpropagation is guided to a feasible solution over the parameter space by initializing the network with the known components of the SAR forward model. Moreover, prior information regarding the waveform structure is incorporated during initialization and backpropagation. We demonstrate the effectiveness of the DL-based approach through extensive numerical simulations that show focused, high contrast imagery using a single receiver antenna at realistic SNR levels.

arXiv:1808.10550

Securing Tag-based recommender systems against profile injection attacks: A comparative study

This work addresses challenges related to attacks on social tagging systems, which often comes in a form of malicious annotations or profile injection attacks. In particular, we study various countermeasures against two types of threats for such systems, the Overload and the Piggyback attacks. The studied countermeasures include baseline classifiers such as, Naive Bayes filter and Support Vector Machine, as well as a deep learning-based approach. Our evaluation performed over synthetic spam data, generated from del.icio.us, shows that in most cases, the deep learning-based approach provides the best protection against threats.

arXiv:1808.08413

A Brief Survey and an Application of Semantic Image Segmentation for Autonomous Driving

Deep learning is a fast-growing machine learning approach to perceive and understand large amounts of data. In this paper, general information about the deep learning approach which is attracted much attention in the field of machine learning is given in recent years and an application about semantic image segmentation is carried out in order to help autonomous driving of autonomous vehicles. This application is implemented with Fully Convolutional Network (FCN) architectures obtained by modifying the Convolutional Neural Network (CNN) architectures based on deep learning. Experimental studies for the application are utilized 4 different FCN architectures named FCN-AlexNet,FCN-8s, FCN-16s and FCN-32s. For the experimental studies, FCNs are first trained separately and validation accuracies of these trained network models on the used dataset is compared. In addition, image segmentation inferences are visualized to take account of how precisely FCN architectures can segment objects.