Return to page

WIKI

Deep Learning Use Cases

What are Deep Learning Use Cases?

Deep learning has been widely used for knowledge discovery and predictive analytics. Google, for example, builds powerful voice- and image-recognition algorithms with deep learning. Netflix and Amazon use deep learning for recommendation engines, and MIT researchers use deep learning for predictive analytics.

Why are Deep Learning Use Cases important?

Deep learning use cases are important because it helps power various kinds of applications. Below are eight reasons why:

Image Recognition

Deep learning is beneficial for computer vision applications, as discussed previously. Google, Facebook, IBM, and others have successfully used deep learning to train computers to recognize human faces and identify the contents of images.

Speech Processing

Deep learning recognizes human speech, converts text into addresses, and processes natural language. As a result, chatbots and voice assistants such as Siri and Cortana can carry on conversations with users based on their context.

Translation

After a deep learning system has been trained to understand one language, the next logical step is to teach it to understand multiple languages and translate between them. Several vendors offer APIs with deep learning-based translation capabilities.

Recommendation Engines

Users have grown accustomed to websites like Amazon and services like Netflix offering recommendations based on their past usage. A lot of these recommendation engines are powered by deep learning. This allows them to improve over time and find hidden correlations in preferences that humans might miss.

Text Mining

Text mining is the process of running analytics on text. Depending on the application, it might be possible to determine the feelings and emotions of the person who wrote the text. You can also extract the main points from a document or compose a summary.

Analytics

Big data analytics has become an integral part of doing business for most enterprises. Machine learning, and specifically deep learning, promises to make predictive and prescriptive analytics even better than they already are.

Forecasting

Upcoming events are one of the most common applications of analytics. Enterprises use deep learning to predict customer demand, supply chain problems, future earnings, etc.

Medicine

Deep learning also has many potential uses in the medical field. It could, for instance, perform better than human radiologists at reading scans and power diagnostic engines that could augment human physicians.

H2O.ai and Deep Learning Use Cases: H2O AI is a platform 

H2O.ai and Deep Learning Use Cases

H2O supports the most widely used statistical & machine learning algorithms including gradient boosted machines, generalized linear models, deep learning, and more.

Read “Deep Learning for Business Leaders” to better understand the rapidly growing discipline that models high-level patterns in data as complex multilayered networks.

Deep Learning Use Cases vs. Other Technologies & Methodologies

Deep learning vs. Artificial intelligence

Deep learning is a subset of machine learning where multilayered neural networks learn from massive data. Artificial intelligence is a program that can sense, reason, act, and adapt to said data.

Deep learning vs. Neural networks

An essential distinction between neural networks and deep learning neural networks is the depth of the hidden layers. The neural network is a model inspired by the human brain consisting of many interconnected neurons.

Deep learning vs. reinforcement learning

Deep learning requires an already existing data set, while reinforcement learning does not.

Deep learning vs. supervised learning

Supervisory machine learning, also known as supervised learning, is a subcategory of machine learning where an algorithm is trained by using labeled data to classify data or predict outcomes based on a labeled dataset. In deep learning, neurons in layers of the neocortex are modeled. It is called deep because it has more than one hidden layer of neurons, enabling multiple nonlinear feature transformation states.