Demystifying Deep Learning: a practical approach in MATLAB

רועי פן, מהנדס יישומי עיבוד תמונה, ראיה ממוחשבת ולמידה עמוקה מסיסטמטיקס בהרצאה בכנס MATLAB Expo Israel 2019

Deep learning can achieve state-of-the-art accuracy in many humanlike tasks such as naming objects in a scene or recognizing optimal paths in an environment.

The main tasks are to assemble large data sets, create a neural network, to train, visualize and evaluate different models, using specialized hardware – often requiring unique programming knowledge. These tasks are frequently even more challenging because of the complex theory behind them.

In this lecture, we’ll demonstrate new MATLAB features that eliminate the low-level programming and that make it easy to:

Manage extremely large sets of images
Visualize networks and gain insight into the black box nature of deep networks
Perform classification and pixel-level semantic segmentation on images
Import training data sets from networks such as GoogLeNet and ResNet
Import and use pre-trained models from TensorFlow and Caffe
Speed up network training with parallel computing on a cluster
Automate manual effort required to label ground truth
Automatically convert a model to CUDA to run on GPUs

[havakok]

זה הרבה פחות סרטון הסברתי והרבה יותר סרטון "אוווו, תראו איזה מוצר מגניב יש לנו. תקנו אותו!". משעמם!!!