5 Facts about Deep Learning and Neural Networks

Marketing staff are much more successful than engineers for things to be adopted. Even for engineering marvels. People working in telecommunication sector might be familiar with that we all called previous wireless mobile communication as wideband code division multiple access. Then, marketing people have taken over the place and named the technology as 3G because it is third generation. People adopted this new term because it is really sympathetic. Similarly, developers in finance sector named process aiming to increase profitability as customer relationship management or CRM. Then, marketing staff have taken over the business again and named this system as loyalty. This new term is adopted by public because it describes intent clearly. Correspondingly, the big term in big data refers to nothing. Nobody cares about the bigness. The only important thing is making value from the data. So, we engineers are talented about misnaming(!)

Luckily, marketing people directly named cloud. If engineers had named this technology, it would most probably be remote computer access. Thanks to Erdem to raise the awareness. He is currently a marketing director who have an engineering background.

---

You may consider to enroll my top-rated machine learning course on Udemy

---

Deep Learning and Neural Networks

Formal definition of deep learning is wide and deep neural networks. Deep refers to number of layers. We need to define neural networks, too. Neural networks are mechanisms modelling human neural system. Well, do we really know how human nervous system work exactly? They are actually just mathematical models. Barbara describes the deep learning realistically

My favorite definition of deep learning is matrix multiplication, a lot of matrix multiplication

Similarly, Francois Chollet defines neural networks in a realistic way.

Neural networks are a sad misnomer. They’re neither neural nor even networks. They’re chains of differentiable, parameterized geometric functions, trained with gradient descent (with gradients obtained via the chain rule). A small set of highschool-level ideas put together

Both neural networks and deep learning seem to be named by marketers. Names might be much deeper than they are. Also, they have a sympathetic and catchy name. Who knows maybe naming might adopt this motivation first, and adoption may trigger the progress.

---

Support this blog if you do like!

    

---