Conference note: 'Validating Black Box Neural Networks'

Machine learning, driven by recent advances in neural net technology, holds much promise, but how to validate any particular model? This note looks at why validation is necessary, and describes some practical techniques for doing so.

Why validate?

Neural nets are practically opaque to a debug walk-through. Reruns against the same training data can yield quite different results because network layers are initialised by random weights and biases, and thus there is no guarantee that the cost func

WARC subscribers can sign in to keep reading

Not a subscriber?

WARC helps you to plan, create and deliver more effective marketing

  • Prove your case and back-up your idea

  • Get expert guidance on strategic challenges

  • Tackle current and emerging marketing themes

WARC consistently delivers valuable insights that help to make me look like an expert in front of my colleagues and clients.

Dasha Boryso
Strategy Partner, Fetch

You’re in good company

We work with 80% of Forbes' most valuable brands* and 80% of the world's top top-of-the-class agencies.

* Top 10 brands