Popular Deep Learning Applications

By Kimberly Cook |Email | Sep 5, 2018 | 5724 Views

Deep Learning is one of the hottest technologies out there. There are many research papers in Deep Learning, and it can be really overwhelming to keep up.

There are many exciting research topics like Generative Adversarial Nets, Auto-encoders, and Reinforcement Learning. The research done in these fields draws awe and interest, however, most of this research is not yet ready to be implemented into the modern software project workflow.

In this article, I will present some popular applications of Deep Learning that are frequently used in web and mobile apps and have great tutorials for getting started.

Discussing Deep Learning outside the realm of science fiction and possibilities of the future, Software Engineers, Business people, and App Developers want to know: How can Deep Learning help me right now?

In the sense that you can find good tutorials and source code detailing how to implement these algorithms; and implementation is relatively easy, here are some applications of Deep Learning that are stable and universally applicable.

Recommendation Engine
Netflix, Amazon, Spotify, and many more apps are reliant on their recommendation engines to enhance user experience and provide a better service to their users. Fortunately for your app, it is not that difficult to get started with your own recommendation engine.

Recommendation Engines land in two broad categories: Content-Based and Collaborative Filtering methods. Content-Based refers to quantizing objects in your app as a set of features and fitting regression models to predict the tendencies of a user based on his or her own data. Collaborative Filtering is more difficult to implement, but performs better as it incorporates the behavior of the entire user base to make predictions for single users.

Both of these strategies are able to leverage deep networks on massive datasets for productive classification and regression performance.

In your experience, you may find that it is best to start out with a Content-Based engine until you have a sizable user-base. From there you may want to switch entirely to Collaborative Filtering or have your system learn a weighting between the two models that optimizes your engine, such as:

pred = x1 * (Content-Based Engine) + x2 * (Collab-Filtering Engine)

Keras Code for Collaborative Filtering
Further Explanation of the Topic

Text Sentiment Analysis
Many apps have comments or comment-based review systems built into their apps. Natural Language Processing research and Recurrent Neural Networks have come a long way and it is now entirely possible to deploy these models on the text in your app to extract higher-level information. This can be very useful for evaluating the sentimental polarity in the comments sections, or extracting meaningful topics through Named-Entity Recognition models.

These models can also be useful for in-house decisions and strategy decisions.

More on how useful Sentiment Analysis can be:
Sample Code
More Sample Code ?? Repo at bottom of article

Chatbots
Another very interesting, science-fiction type of application is Chatbots. Chatbots are seen by many as one of the pillars of the next-generation of user-interfaces on the web. Chatbots can be trained with samples of dialogue and recurrent neural networks. There are many tutorials on how to build chatbots:

Image Recognition
Image retrieval and classification are very useful if your app utilizes images. Some of the most popular approaches include using recognition models to sort images into different categories, or using auto-encoders to retrieve images based on visual similarity. Image recognition tactics can also be used to segment and classify video data, since videos are really just a time-sequence of images.
Popular Strategies to Improve Image Recognition Performance

Marketing Research
In addition to looking for new features that can improve your app, Deep Learning can also be useful behind the scenes. Market segmentation, marketing campaign analysis, and many more can be improved using Deep Learning regression and classification models. This will really help the most if you have a massive amount of data, otherwise, you are probably best using traditional machine learning algorithms for these tasks rather than Deep Learning.

Conclusion
Every time I see a new app, it is easy to imagine how recommendation engines, sentiment analysis, image recognition, and chatbots could improve the functionality of the app. All of these applications have been made possible or greatly improved due to the power of Deep Learning.

Obviously, this is just my opinion and there are many more applications of Deep Learning. However, I think this is a great list of applications that have tons of tutorials and documentation and generally perform reliably. In contrast to something like Generative Adversarial Nets or Reinforcement Learning which are quite tricky to figure out how to integrate into your web or mobile app. I think that these use cases of Deep Learning have a universal applicability to most apps. Additionally, Deep Learning is a subset of Data Science and there are many more ways that Data Science can provide value to your software projects.


The article was originally published here

Source: HOB