{"id":1292,"date":"2019-03-27T04:59:57","date_gmt":"2019-03-27T04:59:57","guid":{"rendered":"https:\/\/blogs.mathworks.com\/deep-learning\/?p=1292"},"modified":"2021-04-06T15:51:06","modified_gmt":"2021-04-06T19:51:06","slug":"whats-new-r2019a-examples","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/deep-learning\/2019\/03\/27\/whats-new-r2019a-examples\/","title":{"rendered":"What’s New R2019a: Examples"},"content":{"rendered":"Hi Everyone! Welcome to R2019a. A new version of MATLAB is available now! I'd like to walk through a few of the new deep learning examples<\/strong>.\r\n
<\/h6>\r\nI categorized the new examples based on their application area.This was a great release for examples, and I guarantee there is something for everyone in this list. Check them out and let me know what you think.\r\n
<\/h6>\r\nImage Processing and Computer Vision Examples<\/span>\r\n\r\n \r\n\r\n\r\n\r\n\r\n
3-D Brain Tumor Segmentation Using Deep Learning<\/span><\/a><\/td>\r\n<\/td>\r\nImage-to-Image Regression*<\/span><\/a><\/td>\r\n<\/td>\r\nTrain a YOLO v2 Object Detector<\/span><\/a><\/td>\r\n<\/td>\r\nClassify Video using Deep Learning<\/span><\/a><\/td>\r\n<\/tr>\r\n
\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/tr>\r\n\r\n<\/tbody>\r\n<\/table>\r\n
<\/h6>\r\n* Remember when I did an article on Image-to-Image Regression<\/a>? This 2nd doc example is much easier to follow and uses new techniques in 19a.\r\n\r\n\r\n
<\/h6>\r\nAudio Examples<\/span>\r\n
<\/h6>\r\n\r\n\r\n\r\n\r\n
Voice Activity Detection in Noise Using Deep Learning<\/span><\/a><\/td>\r\n<\/td>\r\nCocktail Party Source Separation Using Deep Learning Networks<\/span><\/a><\/td>\r\n<\/td>\r\nAcoustic Scene Recognition Using Late Fusion<\/span><\/a><\/td>\r\n<\/tr>\r\n
\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/tr>\r\n\r\n<\/tbody>\r\n<\/table>\r\n
<\/h6>\r\nReinforcement Learning Examples<\/span>\r\n
<\/h6>\r\nReinforcement Learning is a brand-new toolbox to support deep learning for controls. This won\u2019t be the last time you hear about this.\r\n
<\/h6>\r\n\r\n\r\n\r\n\r\n
Train a reinforcement learning agent to solve a grid world problem.<\/span><\/a>\r\n<\/td>\r\n<\/td>\r\nTrain a controller to balance an inverted pendulum in MATLAB using reinforcement learning<\/span><\/a>\r\n\r\n
<\/h6>\r\n This has been described to me as \"Reinforcement Learning 101\", so if you're interested in this topic, start here.<\/span><\/em>\r\n\r\n<\/td>\r\n
<\/td>\r\nTrain a robot to walk in a straight-line using Simulink and reinforcement learning<\/span><\/a><\/td>\r\n<\/tr>\r\n
\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/tr>\r\n\r\n<\/tbody>\r\n<\/table>\r\n
<\/h6>\r\nIf you run the 3rd reinforcement learning example, you will get a cool walking robot. An in-depth video<\/a> will walk you through the example, including the problem setup, neural network design, and speeding up training.\r\n\r\n\"\"\r\n
<\/h6>\r\nSignal and Wavelet Examples<\/span>\r\n
<\/h6>\r\n\r\n\r\n\r\n\r\n
Waveform segmentation using Deep Learning<\/span><\/a><\/td>\r\n<\/td>\r\nModulation Classification<\/span><\/a><\/td>\r\n<\/td>\r\nTexture Classification with Wavelet Scattering<\/span><\/a><\/td>\r\n<\/tr>\r\n
\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/tr>\r\n\r\n<\/tbody>\r\n<\/table>\r\n
<\/h6>\r\nRadar and Comms Examples<\/span>\r\n
<\/h6>\r\n\r\n\r\n\r\n\r\n
Radar Target Classification using Machine and Deep Learning<\/span><\/a><\/td>\r\n<\/td>\r\nRadar Waveform Classification Using Deep Learning<\/span><\/a><\/td>\r\n<\/tr>\r\n
\"\"<\/a><\/td>\r\n<\/td>\r\n\"\"<\/a><\/td>\r\n<\/tr>\r\n\r\n<\/tbody>\r\n<\/table>\r\n
<\/h6>\r\nTake a look at the relevant demos to you and let me know what you think. Also, I'm always curious: how often do you upgrade releases? How do you find out what's new? Leave a comment below.\r\n
<\/h6>\r\nStay tuned for more posts about what's new in 19a!\r\n
<\/h6>\r\n

Follow @jo_pings<\/a>