Deep Learning definition and why it matters
Deep learning is a type of machine learning that trains a computer to perform human-like tasks, such as recognizing speech, identifying images or making predictions. Instead of organizing data to run through predefined equations, deep learning sets up basic parameters about the data and trains the computer to learn on its own by recognizing patterns using many layers of processing.
The evolution of deep learning
Deep learning is one of the foundations of artificial intelligence (AI), and the current interest in deep learning is due in part to the buzz surrounding AI. Deep learning techniques have improved the ability to classify, recognize, detect and describe – in one word, understand.
For example, deep learning is used to classify images, recognize speech, detect objects and describe content. Systems such as Siri and Cortana are powered, in part, by deep learning.
Several developments are now advancing deep learning:
- Algorithmic improvements have boosted the performance of deep learning methods.
- New machine learning approaches have improved accuracy of models.
- New classes of neural networks have been developed that fit well for applications like text translation and image classification.
- We have a lot more data available to build neural networks with many deep layers, including streaming data from the Internet of Things, textual data from social media, physicians notes and investigative transcripts.
- Computational advances of distributed cloud computing and graphics processing units have put incredible computing power at our disposal. This level of computing power is necessary to train deep algorithms.
At the same time, human-to-machine interfaces have evolved greatly as well. The mouse and the keyboard are being replaced with gesture, swipe, touch and natural language, ushering in a renewed interest in AI and deep learning.
Deep Learning for Animal Conservation
How does a computer “see” an image? Jared Peterson, Senior Manager of SAS Advanced Analytics R&D, shows how deep learning neural networks are the science behind computer vision.
In this deep learning example, the computer program is learning to interpret animal tracks to help with animal conservation.
Deep learning opportunities and applications
A lot of computational power is needed to solve deep learning problems because of the iterative nature of deep learning algorithms, their complexity as the number of layers increase, and the large volumes of data needed to train the networks.
The dynamic nature of deep learning methods – their ability to continuously improve and adapt to changes in the underlying information pattern – presents a great opportunity to introduce more dynamic behavior into analytics.
Greater personalization of customer analytics is one possibility. Another great opportunity is to improve accuracy and performance in applications where neural networks have been used for a long time. Through better algorithms and more computing power, we can add greater depth.
While the current market focus of deep learning techniques is in applications of cognitive computing, there is also great potential in more traditional analytics applications, for example, time series analysis.
Another opportunity is to simply be more efficient and streamlined in existing analytical operations. Recently, SAS experimented with deep neural networks in speech-to-text transcription problems. Compared to the standard techniques, the word-error-rate decreased by more than 10 percent when deep neural networks were applied. They also eliminated about 10 steps of data preprocessing, feature engineering and modeling. The impressive performance gains and the time savings when compared to feature engineering signify a paradigm shift.
Deep learning in today's world
The impact that the deep learning has had on the world has been significant – and it’s only getting started. Learn more about what people are saying.
Looking beyond the deep learning hype
Why is deep learning unequaled among machine learning techniques? It has achieved success in a wide range of tasks were difficult for computers to accomplish in the past, especially in the areas of machine perception. Learn more about how deep learning works and why it's not overhyped.
How to do deep learning with SAS®
Find out how deep learning techniques are developed and deployed using SAS software. This step-by-step guide compares multiple neural network models and explains how to use them. You'll get an introduction to deep learning techniques, applications and how SAS supports the creation of deep neural network models.
Analyze streaming sports data with deep learning
SciSports uses streaming data and applies machine learning, deep learning and artificial intelligence to capture and analyze this data, making way for innovations in everything from player recruitment to virtual reality for fans
How is deep learning being used?
To the outside eye, deep learning may appear to be in a research phase as computer science researchers and data scientists continue to test its capabilities. However, deep learning has many practical applications that businesses are using today, and many more that will be used as research continues. Popular uses today include:
Both the business and academic worlds have embraced deep learning for speech recognition. Xbox, Skype, Google Now and Apple’s Siri®, to name a few, are already employing deep learning technologies in their systems to recognize human speech and voice patterns.
One practical application of image recognition is automatic image captioning and scene description. This could be crucial in law enforcement investigations for identifying criminal activity in thousands of photos submitted by bystanders in a crowded area where a crime has occurred. Self-driving cars will also benefit from image recognition through the use of 360-degree camera technology.
Neural networks, a central component of deep learning, have been used to process and analyze written text for many years. A specialization of text mining, this technique can be used to discover patterns in customer complaints, physician notes or news reports, to name a few.
Amazon and Netflix have popularized the notion of a recommendation system with a good chance of knowing what you might be interested in next, based on past behavior. Deep learning can be used to enhance recommendations in complex environments such as music interests or clothing preferences across multiple platforms.
How deep learning works
Deep learning changes how you think about representing the problems that you’re solving with analytics. It moves from telling the computer how to solve a problem to training the computer to solve the problem itself.
A traditional approach to analytics is to use the data at hand to engineer features to derive new variables, then select an analytic model and finally estimate the parameters (or the unknowns) of that model. These techniques can yield predictive systems that do not generalize well because completeness and correctness depend on the quality of the model and its features. For example, if you develop a fraud model with feature engineering, you start with a set of variables, and you most likely derive a model from those variables using data transformations. You may end up with 30,000 variables that your model depends on, then you have to shape the model, figure out which variables are meaningful, which ones are not, and so on. Adding more data requires you to do it all over again.
The new approach with deep learning is to replace the formulation and specification of the model with hierarchical characterizations (or layers) that learn to recognize latent features of the data from the regularities in the layers.
The paradigm shift with deep learning is a move from feature engineering to feature representation.
The promise of deep learning is that it can lead to predictive systems that generalize well, adapt well, continuously improve as new data arrives, and are more dynamic than predictive systems built on hard business rules. You no longer fit a model. Instead, you train the task.
Read more about advanced analytics
- Data lineage: Making artificial intelligence smarterFor AI to reach its full potential, the data feeding its algorithms and models needs to be well-understood. Data lineage plays a vital role in understanding data, making it a foundational principle of AI.
- Key questions to kick off your data analytics projectsThere’s no single blueprint for starting a data analytics project. Technology expert Phil Simon suggests considering these ten questions as a preliminary guide.
- The opportunity of smart grid analyticsWith smart grid analytics, utility companies can control operating costs, improve grid reliability and deliver personalized energy services.
- The future of IoT: On the edgeFrom cows to factory floors, the IoT promises intriguing opportunities for business. Find out how three experts envision the future of IoT.