University of Michigan - Ann Arbor

Deep learning is taking off because as the amount of data and computational power increases, deep learning algorithms perform better than traditional machine learning methods. 

You can improve performance by increasing the scale of the NN or giving it more data. Increasing the scale of the NN often places greater strain on technological systems. The more accessible route is taking advantage of the increase in available data.

“Why is deep learning taking off?” 

Machine Learning Yearning, a free ebook from Andrew Ng, teaches you how to structure Machine Learning projects.
https://www.deeplearning.ai/machine-learning-yearning/

Note: The content of the book is aligned with the Coursera Deeplearning.ai specialization.  https://www.deeplearning.ai/deep-learning-specialization/ 

Machine Learning Yearning (Deeplearning.ai)

https://machinelearning-blog.com/2017/11/03/erster-blogbeitrag/#:~:text=Getting%20a%20better%20accuracy%20with,or%20huge%20amounts%20of%20data.&text=The%20recent%20breakthroughs%20in%20the,use%20more%20and%20more%20data.

If the basic technical ideas behind Deep Learning are around for decades, why are they taking off today? 

https://towardsdatascience.com/how-do-you-know-you-have-enough-training-data-ad9b1fd679ee

Why deep learning is taking off source

https://medium.com/@shaoliang.jia/why-is-deep-learning-taking-off-8244175929e7

Deep learning and its relationship with data

Which of these are reasons for Deep Learning recently taking off?

The curse of dimensionality states that as the number of dimensions (features) in the data increase, the number of categories of interest increases exponentially. This makes using machine learning on high dimensional data difficult.

For a data set with $d$ dimensions and $v$ values to be categorized for each dimension, $O(v^d)$ regions and examples are needed.


Learn Before

Related