Knowledge base

Neural Compression is the conversion, via machine learning, of various types of data into a representative numerical/text format, or vector format. It’s currently promising new and innovative ways of delivering image and video content, by potentially compressing image data into neural networks instead of storing differences or binary values.

In machine learning, generalization is the ability of a trained model to perform effective transformations and inference on data other than the data on which it was trained. In this article we take a look at some of the advantages of and obstacles to good generalization.