Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans – to learn by example. Venture Beat brought this information to us in their article, “This is what makes deep learning so powerful.”
Deep learning is a key technology behind driverless cars, enabling them to recognize a stop sign or to distinguish a pedestrian from a lamppost. It is the key to voice control in consumer devices like phones, tablets, televisions, and hands-free speakers.
The success of deep learning comes primarily from the availability of large data sets and computing power. It is more than that, however, and deep learning is far better than any of the classical machine learning algorithms.
Deep learning is a complex composition of functions from layer to layer finding the function that defines a mapping from input to output. The computer learns the map from input to output and can then apply it in other similar scenarios, from classifying moving objects to assigning an emotional bias to a text based on the way words are used.
It is unfortunate that most organizations have little knowledge regarding how artificial intelligence (AI) systems make their decisions and how the results are applied. Explainable AI – wherein the AI model is not a black box but instead well-described, along with its expected impact and potential biases – allows users to comprehend and trust the results and output created by machine learning algorithms.
Melody K. Smith
| Data Harmony is an award-winning semantic suite that leverages explainable AI. |
|
Sponsored by Data Harmony, harmonizing knowledge for a better search experience.
