Apple Machine Learning Journal

  • However, to achieve high accuracy, the training sets need to be large, diverse, and accurately annotated, which is costly.
  • An alternative to labelling huge amounts of data is to use synthetic images from a simulator.
  • This is cheap as there is no labeling cost, but the synthetic images may not be realistic enough, resulting in poor generalization on real test images.
  • We show that training models on these refined images leads to significant improvements in accuracy on various machine learning tasks.
  • Read the article View the article “Improving the Realism of Synthetic Images”

Most successful examples of neural nets today are trained with supervision. However, to achieve high accuracy, the training sets need to be large, diverse, and accurately annotated, which is costly. An alternative to labelling huge amounts of data is to use synthetic images from a simulator. This is cheap as there is no labeling cost, but the synthetic images may not be realistic enough, resulting in poor generalization on real test images. To help close this performance gap, we’ve developed a method for refining synthetic images to make them look more realistic. We show that training models on these refined images leads to significant improvements in accuracy on various machine learning tasks.
Continue reading “Apple Machine Learning Journal”

GitHub

  • Optional reading material from Michael Nielsen Chapters 1-4 (Do 3-5 of the optional exercises).
  • Optional reading material from Michael Nielsen Chapter 6 (stop when reaching section called Other approaches to deep neural nets).
  • Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE
  • Thanks to professor Ole Winther for supervision and sponsoring the labs.
  • Please note that GitHub no longer supports old versions of Internet Explorer.

tensorflow-tutorial – Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE
Continue reading “GitHub”