Classifying images with Lenet-5 model

by Sujin Kim on 2020-06-19 11:55:08

Date: 2020. 06. 19 (FRI) 15:00 Locate: EB5. 533 Presenter: Sujin Kim Title: Classifying images with Lenet-5 model Article source: https://towardsdatascience.com/a-comprehensive-introduction-to-different-types-of-convolutions-in-deep-learning-669281e58215 Continue reading →

26 Views

이기종 디바이스에서의 CPU, GPU 작업 분할을 이용한 딥러닝 학습 속도 개선

by Donghee Ha on 2020-06-01 15:57:38

Date: 2020. 06. 5 (Fri) 17:30 Locate: EB5. 533 Presenter: Donghee Ha Title: 이기종 디바이스에서의 CPU, GPU 작업 분할을 이용한 딥러닝 학습 속도 개선 Continue reading →

141 Views

Optimizing CNN Model Inference on CPUs

by Seungmin Jeon on 2020-05-25 20:53:59

Date : 2020. 05. 29 (Fri) 15:00 Locate : EB5. 533 Presenter : Seungmin Jeon Title : Optimizing CNN Model Inference on CPUs Author : Yizhi Liu, Yao Wang, Ruofei Yu, Mu Li, Vin Sharma, and Yida Wang, Amazon Abstract : The popularity of Convolutional Neural Network (CNN) models and the ubiquity of CPUs imply that better performance of CNN model inference on CPUs can deliver significant gain to a large number of users. To improve the performance of CNN inference on CPUs, current approaches like MXNet and Intel OpenVINO usually treat the model as a graph and use the high-performance libraries such as Intel MKL-DNN to implement the operations of the graph. While achieving reasonable performance on individual operations from the off-the-shelf libraries, this solution makes it inflexible to conduct optimizations at the graph level, as the local operation-level optimizations are predefined. Therefore, it is restrictive and misses the opportunity to ... Continue reading →

56 Views

Online personalization of cross-subjects based activity recognition models on wearable devices

by Jinyoung Choi on 2020-05-15 18:18:30

Date : 2020. 05. 22 (Fri) 15:00 Locate : EB5. 533 Presenter : Jinyoung Choi Title : Online personalization of cross-subjects based activity recognition models on wearable devices Author : Timo Sztyler, Heiner Stuckenschmidt (University of Mannheim, Germany) Abstract : Human activity recognition using wearable devices is an active area of research in pervasive computing. In our work, we address the problem of reducing the effort for training and adapting activity recognition approaches to a specific person. We focus on the problem of cross-subjects based recognition models and introduce an approach that considers physical characteristics. Further, to adapt such a model to the behavior of a new user, we present a personalization approach that relies on online and active machine learning. In this context, we use online random forest as a classifier to continuously adapt the model without keeping the already seen data available and an active ... Continue reading →

61 Views

Execution Model to Reduce the Interference of Shared Memory in ARINC 653 Compliant Multicore RTOS

by Jihun Bae on 2020-05-11 17:10:34

Date: 2020. 05.15 (Fri) 15:00 Locate: EB5. 533 and Zoom Presenter: Jihun Bae Title: TExecution Model to Reduce the Interference of Shared Memory in ARINC 653 Compliant Multicore RTOS Author: Sihyeong Park, Mi-Young Kwon, Hoon-Kyu Kim, Hyungshin Kim Abstract: Multicore architecture is applied to contemporary avionics systems to deal with complex tasks. However, multicore architectures can cause interference by contention because the cores share hardware resources. This interference reduces the predictable execution time of safety-critical systems, such as avionics systems. To reduce this interference, methods of separating hardware resources or limiting capacity by core have been proposed. Existing studies have modified kernels to control hardware resources. Additionally, an execution model has been proposed that can reduce interference by adjusting the execution order of tasks without software modification. Avionics systems require several rigorous software ... Continue reading →

64 Views

이기종 디바이스에서의 CPU, GPU 작업 분할을 이용한 딥러닝 학습 속도 개선

by Donghee Ha on 2020-05-04 22:11:09

Date: 2020. 01. 20 (Mon) 15:00 Locate: EB5. 533 Presenter: Donghee Ha Title: 이기종 디바이스에서의 CPU, GPU 작업 분할을 이용한 딥러닝 학습 속도 개선 Continue reading →

156 Views

Learning bothWeights and Connections for Efficient Neural Networks

by Juwon You on 2020-04-27 20:05:49

Date: 2020. 05. 01 (Fri) 15:00 Locate: EB5. 533 Presenter: Juwon You Title: Learning bothWeights and Connections for Efficient Neural Networks Author: Song Han, Jeff Poll, John Tran, William J. Dally           (Stanford Univ, NVIDIA, NVIDIA, Stanford Univ & NVIDIA) Abstract: Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional networks fix the architecture before training starts; as a result, training cannot improve the architecture. To address these limitations, we describe a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections. Our method prunes redundant connections using a three-step method. First, we train the network to learn which connections are important. Next, we prune the unimportant connections. Finally, we retrain the ... Continue reading →

92 Views

ADMM-NN: An Algorithm-Hardware Co-Design Framework...

by Jinse Kwon on 2020-04-17 17:00:06

Date : 2020. 04. 24 (Fri) 15:00 Locate : EB5. 533 Presenter : Jinse Kwon Title : ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers   Author : Ao Ren, Tianyun Zhang, Shaokai Ye, Jiayu Li, Wenyao Xu, Xuehai Qian, Xue Lin, Yanzhi Wang (Northeastern University, Syracuse University, SUNY University at Buffalo, University of Southern California)   Abstract : To facilitate efficient embedded and hardware implementations of deep neural networks (DNNs), two important categories of DNN model compression techniques: weight pruning and weight quantization are investigated. The former leverages the redundancy in the number of weights, whereas the latter leverages the redundancy in bit representation of weights. However, there lacks a systematic framework of joint weight pruning and quantization of DNNs, thereby limiting the available model compression ratio. Moreover, the computation ... Continue reading →

103 Views

You Only Look Once: Unified, Real-Time Object Detection

by Jaemin Kang on 2020-04-14 21:20:28

Date: 2020. 04.17 (Fri) 15:00 Locate: EB5. 533 and Zoom Presenter: Jaemin Kang Title: You Only Look Once: Unified, Real-Time Object Detection Author: Joseph Redmon, Santosh Divvala, Ross Girshick, A Li Farhadi Abstract: We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of ... Continue reading →

85 Views

Tightening Contention Delays While Scheduling Parallel Applications on Multi-core Architectures

by Sihyeong Park on 2020-04-06 09:42:43

Date: 2020. 04.10 (Fri) 15:00 Locate: EB5. 533 and Zoom Presenter: Sihyeong Park Title: Tightening Contention Delays While Scheduling Parallel Applications on Multi-core Architectures Author: Benjamin Rouxel, Steven  Derrien, Isabelle  Puaut Abstract: Multi-core systems are increasingly interesting candidates for executing parallel real-time applications, in avionic, space or automotive industries, as they provide both computing capabilities and power efficiency. However, ensuring that timing constraints are met on such platforms is challenging, because some hardware resources are shared between cores. Assuming worst-case contentions when analyzing the schedulability of applications may result in systems mistakenly declared unschedulable, although the worst-case level of contentions can never occur in practice. In this paper, we present two contention-aware scheduling strategies that produce a time-triggered schedule of the application’s tasks. Based on knowledge of ... Continue reading →

101 Views

Portable and Configurable Implementation of ARINC-653 Temporal Partitioing for Small Civilian UAVs

by Jihun Bae on 2020-02-24 11:25:10

Date: 2020. 02. 24 (Mon) 15:00 Locate: EB5. 533 Presenter: Jihun Bae Title: Portable and Configurable Implementation of ARINC-653 Temporal Partitioing for Small Civilian UAVs Author: HYUN-CHUL JO JOO-KWANG PARK, HYUN-WOOK JIN, HYUNG-SIK YOON, AND SANG HUN LEE Abstract: The ARINC-653 standard denes temporal partitioning that enables multiple avionics applications to execute independently from each other without interference in terms of CPU resources. Though partitioning has been mainly discussed from the viewpoint of manned aircraft, it can also efficiently integrate multiple applications on civilian Unmanned Aerial Vehicles (UAVs) that have even severer limitations on size, weight, power, and cost. In order to employ ARINC-653 temporal partitioning to civilian UAVs, its implementation must be flexible enough to be applied to diverse run-time software environments and computing hardware platforms. In this paper, we suggest a portable and configurable implementation ... Continue reading →

163 Views

Environmental Sound Classification on Microcontrollers using Convolutional Neural Networks

by Juwon You on 2020-02-24 09:51:17

Date: 2020. 02. 24 (Mon) 15:00 Locate: EB5. 533 Presenter: Jaemin Kang, Juwon You Title: Environmental Sound Classification on Microcontrollers using Convolutional Neural Networks Author: Jon Nordy Abstract: Noise is a growing problem in urban areas, and according to the WHO is the second environmental cause of health problems in Europe. Noise monitoring using Wireless Sensor Networks are being applied in order to understand and help mitigate these noise problems. It is desirable that these sensor systems, in addition to logging the sound level, can indicate what the likely sound source is. However, transmitting audio to a cloud system for classification is energy-intensive and may cause privacy issues. It is also critical for widespread adoption and dense sensor coverage that individual sensor nodes are low-cost. Therefore we propose to perform the noise classification on the sensor node, using a low-cost microcontroller. Several Convolutional Neural Networks ... Continue reading →

127 Views

by Juwon You on 2020-02-24 09:35:22

                Continue reading →

0 Views

Split-CNN: Splitting Window-based Operations in CNN for Memory System Optimization

by Donghee Ha on 2020-01-23 14:43:44

Date: 2020. 01. 20 (Mon) 15:00 Locate: EB5. 533 Presenter: Donghee Ha Title: Split-CNN: Splitting Window-based Operations in Convolutional Neural Networks for Memory System Optimization Author: Tian Jin, Seokin Hong Abstract: We present an interdisciplinary study to tackle the memory bottleneck of training deep convolutional neural networks (CNN). Firstly, we introduce Split Convolutional Neural Network (Split-CNN) that is derived from the automatic transformation of the state-of-the-art CNN models. The main distinction between Split-CNN and regular CNN is that Split-CNN splits the input images into small patches and operates on these patches independently before entering later stages of the CNN model. Secondly, we propose a novel heterogeneous memory management system (HMMS) to utilize the memory-friendly properties of Split-CNN. Through experiments, we demonstrate that Split-CNN achieves significantly higher training scalability by dramatically reducing the memory ... Continue reading →

183 Views

Hips Do Lie! A Position-Aware Mobile Fall Detection System

by Jinyoung Choi on 2020-01-19 18:22:58

Date: 2020. 01. 20 (Mon) 15:00 Locate: EB5. 533 Presenter: Jinyoung Choi Title: Hips Do Lie! A Position-Aware Mobile Fall Detection System 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom) Author: Christian Krupitzer, Timo Sztyler, Janick Edinger, Martin Breitvach, Heiner Stuckenschmidt, Christian Becker  Abstract: Ambient Assisted Living using mobile device sensors is an active area of research in pervasive computing. Multiple approaches have shown that wearable sensors perform very well and distinguish falls reliably from Activities of Daily Living. However, these systems are tested in a controlled environment and are optimized for a given set of sensor types, sensor positions, and subjects. In this work, we propose a self-adaptive pervasive fall detection approach that is robust to the heterogeneity of real life situations. Therefore, we combine sensor data of four publicly available datasets, covering about 100 subjects, ... Continue reading →

136 Views