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”

Building AI: 3 theorems you need to know – DXC Blogs

Building #AI: 3 theorems you need to know #MachineLearning

  • The mathematical theorem proving this is the so-called “no-free-lunch theorem” It tells us that if a learning algorithm works well with one kind of data, it will work poorly with other types of data.
  • In a way, a machine learning algorithm projects its own knowledge onto data.
  • In machine learning, overfitting occurs when your model performs well on training data, but the performance becomes horrible when switched to test data.
  • Any learning algorithm must also be a good model of the data; if it learns one type of data effectively, it will necessarily be a poor model — and a poor student – of some other types of data.
  • Good regulator theorem also tells us that determining if inductive bias will be beneficial or detrimental for modeling certain data depends on whether the equations defining the bias constitute a good or poor model of the data.

Editor’s note: This is a series of blog posts on the topic of “Demystifying the creation of intelligent machines: How does one create AI?” You are now reading part 3. For the list of all, see here: 1, 2, 3, 4, 5, 6, 7.
Continue reading “Building AI: 3 theorems you need to know – DXC Blogs”