Skip to main content

WTF is Deep Learning Anyway

Following on my previous WTF post on Machine Learning, it just make sense to continue in this line of thought to address another of many popular and trendy concepts. We are talking about: Deep Learning.

So without further due, lets explain WTF is deep learning shall we?

Simply put, and as inferred from the previous post mentioned, deep learning is one of  now many approaches to machine learning we can find out there, along the lines of other approaches like decision tree learning, association rule learning, or Bayesian networks.

While deep learning is not new, was introduced by Dr. Rina Dechter in 1986, its until recent years that this approach have gained fame and popularity among users and particularly among software companies adopting it within their analytics arsenals.

Deep learning enables to train the computer to perform tasks including recognizing speech, identifying images or making predictions by, instead of organizing data to run through predefined equations, sets up basic parameters about the data and train the computer so it can “learn” by recognizing patterns and by executing many layers of processing.

So, What Has Made Deep Learning so Popular?

Many factors have played out to enable the popularity of machine learning in general as well as deep learning in articular.

Today, modern deep learning can provide a powerful framework for supervised learning and for addressing increasingly complex problems, consequently it has gained huge popularity in many fields of computing, including computer vision, speech and audio recognition, natural language processing (NLP), bioinformatics, drug design and many others but, why?

This popularity have to do on one hand, of course, with the fast evolution of deep learning algorithms but also, due to the converged evolution of core computer processing related technologies including big data, cloud computing or in-memory processing which has enabled deep learning algorithms which require intensive computer resources to be deployed in increasingly faster and more efficient computing infrastructures.

On the other, due to the evolution and consumerization of peripheral technologies like mobile and smart devices  which have made it possible to providers to embed deep learning functionality within increasing systems and for increasing use cases and reach more audiences that can use and develop deep learning in a more “natural” way.

How Does Deep Learning Works?

In general, most deep learning architectures are constructed from a type of computing system called artificial neural networks (ANN) —I know, we will get to its own WTF soon— yet they can also include other computing structures and techniques so, Inspired by the structure and the functions of the brain, deep learning usage of ANN’s recreates the interconnection of neurons by developing algorithms that mimic the biological structure of the brain.

Within an ANN, units (neurons) are organized in discrete layers and connected to other units so that each layer choses a specific feature to learn (shapes, patterns, etc.). Each layer creates a depth of “learning” or “feature to learn” so that, by adding more layers and more units within a layer, a deep network can represent functions of increasing complexity or depth. Is this layering or depth that gives the deep learning its name (Figure 1).

Figure 1.  A 3-layer neural network with three inputs, two hidden layers of 4 neurons each and one output layer. (Source: CS231n Convolutional Neural Networks for Visual Recognition)

Until now most, if not all, deep learning applications deal with tasks or problems that, as the previous figure shows, consist on mapping an input vector to an output vector, allowing the solving of problems that require large enough models and large enough datasets.

These problems are  commonly those that humans would solve relatively easy and without a need to reflect on them (identify forms and shapes, for example), and yet due to the increasing computing power available and the continuous evolution of deep learning, are now allowing computers to perform even faster than humans.

It's clear then that both machine learning in general, and deep learning in particular change the common paradigm for analytics by, instead of developing an algorithm or algorithms to instruct a computer system on how to specifically solve a problem, a model is developed and trained so that the system can “learn” and solve the problem by itself (Figure 2).

Figure 2.  Traditional programming vs Machine learning approaches. (Source: CS231n Convolutional Neural Networks for Visual Recognition)

A key advantage of deep learning is that while a traditional approach will start by using the available data to perform feature engineering and then select a model to estimate parameters within an often repetitive and complex cycle to finally get to an effective model, deep learning replaces it with layer approach in which each layer can recognize key features from patterns or regularities from the data.

Hence, deep learning replaces the formulation of a model using instead characterizations (or layers) organized hierarchically  that can “learn” to recognize features from the available data (Figure 3), which result in the construction of "systems of prediction" that can:

  • Avoid use of hard parameters and business rules
  • Make better generalizations
  • Improve continuously

Figure 3.  Machine learning vs Deep learning. (Source: Xenonstack)

On the downside side, one common challenge when deploying and application of deep learning is it requires intensive computational power due to:

  1. The iterative nature of deep learning algorithms
  2. The increasing complexity as amount of layers increases
  3. The need for large volumes of data to train the neural networks

Still, deep learning’s continuous improvement feature sets an ideal stage for any organization to implement dynamic behavior features within their analytics platforms.

Applications of Deep Learning?

Today, deep learning has already applied in many industries and lines of businesses and, it keeps increasing at a constant pace. Some areas where deep learning has been successfully applied include:

Recommendation Systems

This is perhaps the flagship use case for machine learning and deep learning, companies including Amazon and Netflix have worked on using these systems to develop systems that can, with good chances of assertion, know what a viewer might be interested in watching or purchasing next, after his/her past behavior.

Deep learning enhances their recommendations in complex environments by increasingly learning users interests across multiple platforms.

Image and Speech Recognition

Another common applications of deep learning in the software industry is speech and image recognition, on the speech recognition aspect, companies like Google, Apple and Microsoft have applied deep learning to products like Google Now, Siri and Cortana to recognize voice patterns and human speech.

One the image recognition side, regardless of how challenging can be, it’s possible to find projects already applying deep learning with different levels of success, companies like DeepGlint are using deep learning to recognize and acquire real-time insights from the behavior of cars, people and practically any object.

Applications like this have huge potential in sectors including law enforcement or self-driving cars.

Natural Language Processing

Neural networks and deep learning had been key for the development of natural language processing (NLP), an area of artificial intelligence that develops techniques and solutions that allow “natural” interaction between computers and human languages, especially to enable the processing of large amounts of natural language data.

Companies like MindMeld use deep learning and other techniques to develop intelligent conversational interfaces.

We could go on describing more use cases for deep learning but perhaps its is fair to say the number and types of applications for deep learning keep growing.

What is Out There in the Market?

Currently there are varied options for using or deploying deep learning, both to start experimenting and developing or, to deploy enterprise ready solutions that apply deep learning.

For those organizations with the will for development and innovation, open source based deep learning frameworks and analytics like Tensorflow, Caffe or Pytorch represent a great opportunity to get them up and running.

Other great solutions for developing and applying deep learning solutions include data science platforms like Dataiku, Datarobot or, just recently acquired by Oracle.

Also, users and organizations can take a practical approach and use niche vertical solutions like cloud-native endpoint protection platform CrowdStrike, healthcare software provider Flatiron Health, or security intelligence & analytics (SIA) company Endgame among many others.

Today deep learning and machine learning solutions are increasingly available for small, medium and large companies while, promoting a continuous and fast evolution of these techniques within the market landscape, no surprisingly, expectations are high from users to address and solve increasingly complex problems.

It also hints that perhaps, with new advances and techniques seeing the light of day so frequently, we are just at the beginning of a new era in the analytics marketplace.

It seems deep learning is no joke, or is it?


  1. Next Generation ERP Software - Focus 9

  2. Top ERP Software providers in Asia Pacific - Focus Softnet

  3. Machine learning is a field of information technology that only the smartest people can do. even the most intelligent humanity, for example, how the one that works for the best essay writing service (that also propose writing essay that has a type "essay about yourself"/"essay about myself") cannot understand machine learning.

  4. However, its additional potential does not end here. AI can likewise support worker commitment by improving the organization culture. machine learning certification

  5. There are numerous elements which have added to its remarkable fame. Any semblance of which will be examined as we progress through the article.ExcelR Data Science Courses

  6. I really impressed after read this because of some quality work and informative thoughts . I just wanna say thanks for the writer and wish you all the best for coming!. bank alfalah visa classic credit card | bank alfalah ultra cashback credit card

  7. Remarkable blog! I have no words to praise, it has really allured me.Florence Residences Floor plan

  8. Its been quite long time that I have gone through such good article,I appreciate the effort that you people made in order to bring out such good article

    data science training in aurangabad
    data science course in aurangabad

  9. Great to become visiting your weblog once more, it has been a very long time for me. Pleasantly this article i've been sat tight for such a long time. I will require this post to add up to my task in the school, and it has identical subject along with your review. Much appreciated, great offer.

  10. here are so many online platforms, offering the services today and to get the best rates you must at least compare. transfer money

  11. Its as if you had a great grasp on the subject matter, but you forgot to include your readers. Perhaps you should think about this from more than one angle.
    Best Institutes For Digital Marketing in Hyderabad


  12. Regular visits listed here are the easiest method to appreciate your energy, which is why why I am going to the website everyday, searching for new, interesting info. Many, thank you!
    business analytics course

  13. Great post, thanks for sharing.
    Digital Marketing is right now the most stable job you could have. There are many openings for Digital Marketers around the globe. Hence we suggest you to attend our digital marketing course in Hyderabad to acquire skills that a Digital Marketer needs.
    Digital Marketing Course in Hyderabad

  14. Best Midi Keyboard Controllers
    finding the right keyboard controller can be a hectic and tough job.
    Visit: Best Midi Keyboard Controllers

  15. The pour point depressant market has witnessed significant growth in recent years and this growth is projected to persist in the coming years. PPDs are widely used in the lubricant industry and oil & gas industry to enhance pour point and flow characteristics for effective handling of crude oil in transportation, storage, and processing. They are also widely used as additives in mineral oil lubricants and in middle distillates such as diesel and kerosene. The pour point depressant market is driven by increased growth in the automotive industry and also the refining activities and capacity across the world. The growth of the lubricant industry is coupled with rapid industrialization in economies such as U.S., China, and Japan. The increasing demand for API Group II and III base oils is another factor that is positively influencing the market growth.

  16. Best Wonderchef Induction Cooktop in India
    Wonderchef is a leader in cookware and kitchen appliances that enable our customers to cook healthy, tasty food with convenience. German standards of quality, Italian designs, & constant innovation are the hallmarks of Wonderchef.
    Visit: Best Wonderchef Induction Cooktop in India

  17. Really impressed! Everything is very open and very clear clarification of issues. It contains truly facts. Your website is very valuable. Thanks for sharing.
    data scientist certification malaysia

  18. Authorities think that the very reason behind tricholomania could be the hydrogen rich water stick imbalance regarding compounds inside the neural. These kind of toxins, identified as neurotransmitters will be a part of your brain’s verbal exchanges centre. Whenever a little something reduces how neurotransmitters job it could possibly result in complications similar to compulsive symptoms. dark web sites

  19. Thanks for sharing this.,
    Leanpitch provides online training in Scrum Master, everyone can use it wisely.
    Join Leanpitch 2 Days CSM Certification Workshop in different cities.

    Scrum master certification

    csm certification

  20. Thanks for sharing this.,
    Leanpitch provides online training in Scrum Master, everyone can use it wisely.
    Join Leanpitch 2 Days CSM Certification Workshop in different cities.

    csm training

    Scrum master Training

  21. Nice article. it really impressed of this website. it is very valuable and informative for me. Thanks for sharing these information with all of us. whatsapp mod

  22. Admisionkaro is an individual education consultant who helps the parents, students as well as the organization with education planning.
    Visit: Admission Karo

  23. An epilator is an electrical device that removes multiple strands of hair by pulling them out from the skin.
    Visit: Best Epilators in India

  24. First You got a great blog .I will be interested in more similar topics. i see you got really very useful topics, i will be always checking your blog thanks.
    cyber security training malaysia

  25. we help you find meaning of weed VT in Hindi, weed VT Hindi, weed VT meaning in Hindi, weed VT synonyms in Hindi.
    Visit: Weed Meaning in Hindi

  26. Radiv reviews is a top product review site in India. Visit us to know more.
    Radiv India

  27. At Rainbow Bridge, we can help make that journey a little easier with our specially curated music production course which will introduce you to the basics of music production using the right tools and software, and the essentials of mixing and mastering a track.
    Visit: Diploma in Music Production in India


  28. I am really very happy to visit your blog. Directly I am found which I truly need. please visit our website for more information
    Data labeling service providers in usa

  29. Modern deep learning can provide a powerful framework for supervised learning and for addressing. Thanks for sharing this article. Now it's time to avail 1 litre water bottle for more information.


Post a Comment

Popular posts from this blog

Machine Learning and Cognitive Systems, Part 2: Big Data Analytics

In the first part of this series, I described a bit of what machine learning is and its potential to become a mainstream technology in the industry of enterprise software, and serve as the basis for many other advances in the incorporation of other technologies related to artificial intelligence and cognitive computing. I also mentioned briefly how machine language is becoming increasingly important for many companies in the business intelligence and analytics industry. In this post I will discuss further the importance that machine learning already has and can have in the analytics ecosystem, especially from a Big Data perspective. Machine learning in the context of BI and Big Data analytics Just as in the lab, and other areas, one of the reasons why machine learning became extremely important and useful in enterprise software is its potential to deal not just with huge amounts of data and extract knowledge from it—which can somehow be addressed with disciplines such as data

Next-generation Business Process Management (BPM)—Achieving Process Effectiveness, Pervasiveness, and Control

The range of what we think and do is limited by what we fail to notice. And because we fail to notice that we fail to notice there is little we can do to change until we notice how failing to notice shapes our thoughts and deeds. —R.D. Laing Amid the hype surrounding technology trends such as big data, cloud computing, or the Internet of Things, for a vast number of organizations, a quiet, persistent question remains unanswered: how do we ensure efficiency and control of our business operations? Business process efficiency and proficiency are essential ingredients for ensuring business growth and competitive advantage. Every day, organizations are discovering that their business process management (BPM) applications and practices are insufficient to take them to higher levels of effectiveness and control. Consumers of BPM technology are now pushing the limits of BPM practices, and BPM software providers are urging the technology forward. So what can we expect from the next

Teradata Open its Data Lake Management Strategy with Kylo: Literally

Still distilling good results from the acquisition of former consultancy company Think Big Analytics , Teradata , a powerhouse in the data management market took one step further to expand its data management stack and to make an interesting contribution to the open source community. Fully developed by the team at Think Big Analytics, in March of 2017 the company launched Kylo –a full data lake management solution– but with an interesting twist: as a contribution to the open source community. Offered as an open source project under the Apache 2.0 license Kylo is, according to Teradata, a new enterprise-ready data lake management platform that enables self-service data ingestion and preparation, as well the necessary functionality for managing metadata, governance and security. One appealing aspect of Kylo is it was developed over an eight year period, as the result of number of internal projects with Fortune 1000 customers which has enabled Teradata to incorporate several be