Demystifying Deep Learning: Semantic Segmentation and Deployment
Overview
Deep learning can achieve state-of-the-art accuracy for many tasks considered algorithmically unsolvable using traditional machine learning, including classifying objects in a scene or recognizing optimal paths in an environment. In this webinar, we’ll decipher practical knowledge of the domain of deep learning, and demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. From prototype to production: we’ll build and train neural networks, and discuss automatically converting a model to CUDA to run natively on GPUs.
Note: This webinar builds on concepts previously discussed in the Deep Learning for Computer Vision webinar.
Highlights
- Perform pixel-level semantic segmentation on images
- Import and use pre-trained models from TensorFlow and Caffe
- Speed up network training with parallel computing on a cluster
- Use data augmentation to increase the accuracy of a deep learning model
- Automatically convert a model to CUDA to run on GPUs
About the Presenters
Abhijit Bhattacharjee is a Senior Application Engineer at MathWorks, specializing in the areas of computer vision, audio signal processing, and machine learning. Prior to MathWorks, Abhijit was a researcher at USC Information Sciences Institute, working in programs funded by NASA and DARPA. Projects included hyperspectral image processing and audio steganography. He holds an M.S.E.E. degree from the University of Southern California and works with clients in all industries, including consumer devices, semiconductors, government, and academic.
Pitambar Dayal is a Technical Marketing Manager for MathWorks Image Processing and Computer Vision products. Prior to MathWorks, Pitambar earned his B.S. studying Biomedical Engineering at NJIT and working in a brain-imaging lab, where he researched fMRI patterns in ischemic stroke patients (using MATLAB, of course). Outside of work, Pitambar spends his time traveling, watching basketball, and playing ultimate frisbee. His favorite food is Margherita Pizza and his favorite dessert is Belgian waffles.
Recorded: 26 Jul 2018
Featured Product
Computer Vision Toolbox
Up Next:
Related Videos:
Web サイトの選択
Web サイトを選択すると、翻訳されたコンテンツにアクセスし、地域のイベントやサービスを確認できます。現在の位置情報に基づき、次のサイトの選択を推奨します:
また、以下のリストから Web サイトを選択することもできます。
最適なサイトパフォーマンスの取得方法
中国のサイト (中国語または英語) を選択することで、最適なサイトパフォーマンスが得られます。その他の国の MathWorks のサイトは、お客様の地域からのアクセスが最適化されていません。
南北アメリカ
- América Latina (Español)
- Canada (English)
- United States (English)
ヨーロッパ
- Belgium (English)
- Denmark (English)
- Deutschland (Deutsch)
- España (Español)
- Finland (English)
- France (Français)
- Ireland (English)
- Italia (Italiano)
- Luxembourg (English)
- Netherlands (English)
- Norway (English)
- Österreich (Deutsch)
- Portugal (English)
- Sweden (English)
- Switzerland
- United Kingdom (English)
アジア太平洋地域
- Australia (English)
- India (English)
- New Zealand (English)
- 中国
- 日本Japanese (日本語)
- 한국Korean (한국어)