Facts You Must Know About DL (Deep Learning)

deep learning facts

Hey Everyone! Today we're going to explore some of the truths of Deep Learning that you might not know about. So, without more text let's get started with the first truth.. 

1. Deep Learning is not Artificial General Intelligence 

Deep Learning can do some fantastic things like cross translate between different human languages and read out captions from images. However, the intelligence is really specialized and narrow. Sure DL can drive cars, but that's nowhere near the capability of AGI. 

2. Deep Learning is not Statistics 

Classical statistics is about analyzing data using aggregate measures. DL systems however work in a domain that statistical methods do not apply. That is high-dimensional data with high mutual information among the variables. Simplifying i.i.d assumptions are simply not applicable.

3. Deep Learning is Radically different from Machine Learning 

Machine Learning in its most basic distillation is "curve fitting". That is, if you have an algorithm that is able to find the best fit of your mathematical model with observed data, then that's Machine Learning. 

Deep Learning at its earlier incarnation was about "curve fitting", however it has progressed beyond that in recent years. Deep Learning Meta-Learning should be a big indicator to anyone that this is indeed very different.

4. Deep Learning does not mimic Biological Brains 

The architecture of DL are no where close to a biological neuron in structure. Even in behavior they are different, biological neurons work on spiking behavior, DL system work in a continuous dynamical system. 

Some DL systems use Artificial Neural Networks, but that is just historical terminology that exists to this day. Anyone explaining DL in terms of biological neurons really doesn't know what they are talking about. DL isn't designed to 'mimic' biology, DL just happens to be a computational architecture that learns surprisingly well. 

5. Deep Learning is not "Just Math" 

There was a Wired article titled "Deep Learning isn't a Dangerous Genie, it is Just Math". This is really the most vacuous statement I've heard! It is like saying that computers are just boolean circuits or brains are just made up of neurons or DL are made up of layers that are described using mathematical functions. It doesn't explain the emergent complex behavior you find in computers, brains and DL systems. 

6. Deep Learning in not Good Old Fashion Al (GOFAI) 

Expert systems, semantic web, deductive logic systems etc. are examples of systems that are based on symbolic logic. These systems are typically associated with Al. These do work, however they have one short coming, they are unable to effectively learn from the data. 

7. Deep Learning is not Big Data 

Big Data is a technology that is based on the idea that if you are able to store and compute through a massive amount of data, typically hosted in hundreds or thousands of off-the-shelf computers, then you can gain insight. 

DL is an algorithm that can sit on a single machine and can incrementally, special emphasis on incrementally, process your data to learn from it. Big Data can crunch massive amounts of data, but just because you can process a lot of data doesn't mean you can derive insight or learn from the data. One last point, unlike Big Data, DL doesn't need a lot of data to be useful.

8. Deep Learning is not understood by Data Scientists
Data Scientists are trained to do modeling of data, feature engineering and data analysis. DL just does what a Data Scientist does but without a human in the loop. This is actually a bit of an exaggeration. The reality is that most Data Scientists trained in other methods have not come up to speed with DL techniques. 

9. Deep Learning is not just ANNs or Multi Level Perceptrons

Artificial Neural Networks or ANNs or MLPs were developed way back in the 1950s. DL systems originate from this earlier work, however in recent years they've evolved to new kinds of models like Convolution networks, Long Short Term Memory, Residual Networks etc. The field has a much richer collection of concepts that existed when you studied it in graduate school. 

10. Deep Learning is the reason for the current Al hype 

Finally, this is where the greatest confusion exists. On a daily basis, the press continues to report the amazing progress of Al. Furthermore, you hear about firms like Google and Microsoft changing their entire software DNA to move into Al. The reason for this massive migration is because of Deep Learning. The big problem for the majority of the readers is that, the phrase itself "Deep Learning" is just too difficult to comprehend.

So, Did you already knew about this facts or they are new for you? Tell us on our social medias. And if you have more valuable facts about Deep Learning then please don't hesitate to share with us.