서울 양재 엘타워 5층 | 2018년 5월 29일
NVIDIA Deep Learning Institute는 개발자, 데이터 사이언시스트, 그리고 엔지니어들을 위한 핸즈온 방식의 교육 프로그램입니다. 자율 주행 자동차, 헬스케어, 온라인 서비스, 그리고 로보틱스에 이르기까지 딥 러닝 기술이 필요한 다양한 분야에서 어떻게 딥 뉴럴 네트워크를 어떻게 설계하고 훈련하며 배포하는지에 대한 최신 기술 강의를 들으실 수 있습니다.
지금 바로 NVIDIA DLI DAY 2018 에 등록하시고 가장 최신의 딥 러닝 기술을 배워가시기 바랍니다.
본 핸즈온 세션 참여를 위해서는 본인의 노트북(Windows, Mac, Linux/Wifi/크롬 브라우저)을 소지하고 오셔야 하며, 사전 세팅 사항 완료 및 및 온라인 기본 교육을 사전에 수강하고 오셔야합니다.
서울 양재 엘타워 5층
서울특별시 서초구 양재동 24
2018년 5월 29일(화)
This label explores various approaches to the problem of semantic image segmentation, which is a generalization of image classification where class predictions are made at the pixel level. In this lab we will use the Sunnybrook Cardiac Data to train a neural network to learn to locate the left ventricle on MRI images. On completion of this lab, you will understand how to use popular image classification neural networks for semantic segmentation, you will learn how to extend Caffe with custom Python layers, you will become familiar with the concept of transfer learning and you will get to train two neural networks from the family of Fully Convolutional Networks (FCN).
This lab will introduce three approaches for neural network deployment. The first approach teaches you to use inference functionality directly within a deep learning framework (NVIDIA DIGITS and Caffe). The second approach teaches you how to integrate inference within a custom application by using a deep learning framework API (Caffe, through its Python API). The final approach teaches you to use TensorRT, which will automatically create an optimized inference run-time from a trained Caffe model and network description file. As you explore these approaches, you will learn about the role of batch size in inference performance, as well as various optimizations that can be made in the inference process. You will also explore inference for a variety of different DNN architectures trained in other DLI labs.
Electronic Health Records (EHRs) contain a wealth of patient medical information that can: save valuable time when an emergency arises; eliminate unnecesary treatment and tests; prevent potentially life-threatening mistakes; and, can improve the overall quality of care a patient receives when seeking medical assistance. Children's Hospital Los Angeles (CHLA) wanted to know if the records could be mined to yield early warning signs of patients that may require extra care or an indication of the severity of a patient's illness. In this lab we have access to the work and results of CHLA's applied use of deep neural networks on EHRs belonging to roughly 5,000 pediatric ICU patients.
We will use deep learning techniques to provide medical professionals an analytic framework to predict patient mortality at any time of interest. Such a solution provides essential feedback to clinicians when trying to assess the impact of treatment decisions or raise early warning signs to flag at risk patients in a busy hospital care setting.
In this lab we will use the python library pandas to manage the dataset provided in HDF5 format and deep learning library Keras to build recurrent neural networks (RNN). In particular, this lab will construct a special kind of deep recurrent neural network that is called a long-short term memory network (LSTM). Finally, we will compare the performance of this LSTM approach to standard mortality indices such as PIM2 and PRISM3 as well as contrast alternative solutions using more traditional machine learning methods like logistic regression.