C2 / 深度學習大揭密:利用MATLAB駕馭它的實用秘訣
Demystifying deep learning: A practical approach in MATLAB

Tim Jones / MathWorks Inc.


深度學習的主要任務通常是把大型的資料數據集整合起來,其後建立神經網絡、加以訓練,可視覺化和評估不同模型,也需要使用專門的硬體 - 通常需要獨特的程式編寫知識。由於其背後的複雜理論,這些任務往往充滿著極高的挑戰性。



• 管理極龎大的圖像集
• 將網絡可視覺化,深入探究了解神經網絡的神秘面紗
• 對圖像進行分類和像素級語義分割
• 如何輸入GoogLeNet和ResNet等網絡並進行資料訓練
• 從TensorFlow和Caffe導入和使用預先訓練的模型
• 透過電腦叢群進行平行計算,加快網絡訓練
• 可將手動地面真實標誌的工作改為自動化
• 能自動將模型轉換為CUDA程式並在GPU上運行


Are you new to deep learning and want to learn how to use it in your work? 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 session, we will demonstrate new MATLAB features that simplify these tasks and eliminate low-level programming. In doing so, we will extract practical knowledge of the deep learning network. We will build and train neural networks that recognize handwriting, classify food in a scene, and figure out the drivable area in a city environment.

Along the way, you will see MATLAB features 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