Putting neural networks under the microscope
01 February 2019
Rob Matheson | MIT News

Researchers pinpoint the “neurons” in machine-learning systems that capture specific linguistic features during language-processing tasks.

Researchers from MIT and the Qatar Computing Research Institute (QCRI) are putting the machine-learning systems known as neural networks under the microscope.

In a study that sheds light on how these systems manage to translate text from one language to another, the researchers developed a method that pinpoints individual nodes, or “neurons,” in the networks that capture specific linguistic features.

Full story at MIT News: http://news.mit.edu/2019/neural-networks-nlp-microscope-0201​