Getting Started With Deep Learning

Deep learning's main advantage is that it can handle massive amounts of data - particularly unstructured - well. Getting started doesn't have to be hard by leveraging publicly available pre-trained deep learning models to begin.

Talking about AI is increasingly complex because it’s often used alongside (or even interchangeably with) the terms machine learning (ML) and deep learning (DL). Why do people use these terms relatively interchangeably, and what are the distinctions?

AI-ML-DL-graphic

A deep learning algorithm is able to learn hidden patterns from the data by itself, combine them together, and build much more efficient decision rules. That’s why it can deal with problems that a human brain could not understand – the value of deep learning is this automatic pattern identification capability. This means handling more complex problems, such as understanding concepts in images, videos, texts, sounds, time series, etc.

But don’t think of deep learning as a model learning by itself. It still requires properly labeled data, an evaluation of the model results, and of course an evaluation of the business value it will bring. And the lack of precisely labeled data is one of the main reasons deep learning can have disappointing results in some business cases.

Watch Video

Deep Learning Basics

get the guidebook

Deep Learning in Dataiku

Dataiku is the platform democratizing access to data and enabling enterprises to build their own path to AI. Get started with deep learning in Dataiku quickly with the plugin that leverages publicly available pre-trained deep learning models:

  1. First, add images into Dataiku.
  2. Then import a pre-trained model via the plugin (e.g., Imagenet pre-trained models).
  3. Using transfer learning, retrain the model with the images added in step 1. This adds an extra layer to the neural network that is entirely customized to those images.
  4. Take a new set of images and classify them using the retrained model.

Building and Deploying Models, Made Easy

The key to delivering business value from raw data lies in the organization's ability to go beyond the limits of small data and create machine learning models at scale.

Read more

Go Further

Dataiku für Data Scientists

Bauen Sie Ihr Data-Science- und ML-Wissen aus und verbringen Sie mehr Zeit mit Aufgaben, die Ihr Unternehmen voranbringen.

Learn More

Programmierung in Dataiku

Dank Dataiku werden Sie durch Codierung und Programmierung zum erstklassigen Bürger der Plattform.

Learn More

Einsatz von ML-Modellen im Produktionsbetrieb

Mit Dataiku können Sie Ihre ML-Modelle mit nur einem Klick im Produktionsbetrieb einsetzen und dort von hoher Leistung, skalierbarem Scoring und cloudbasierter Bereitstellung mit Kubernetes profitieren.

Learn More

Dataiku: A Gartner Magic Quadrant Leader

Dataiku was named a Leader in the Gartner 2020 Magic Quadrant for Data Science and Machine-Learning Platforms.

Learn More