So, I think it's a little misleading to say that deep learning eliminates the need for feature engineering. If we're going to provide business value to a company, we're often dealing with somewhat structured data and not "unstructured blobs of pixels or blobs of text". There are several simple linear models with highly engineered features in production where I work that resist attempts to replace them with more clever models and less feature engineering.
Deep learning is awesome and there may be a time when it solves every problem. But let's not oversell it. For now, if someone wants to do machine learning and get paid for it, they're more likely to see their colleagues using the techniques in this article than training deep multi-layer neural nets.
Even in non-image data competitions, a deep neural network will often be one of the models chosen to ensemble. They generally perform slightly worse than XGBoost models, but have the advantage that they often aren't closey correlated, which helps fighting overfitting when tuning ensembling hyperparamters.
What it DOES is shifts the problem to layer architectures which is a hard problem in and of itself:
What vonnik is talking about and what's already been addressed in a sibling comment was images.
"Features" are the pixels which handles generating the "baseline representation" needed for feature engineering.
Another thing of note here is it just highlights that ETL is important. Eg: image sizes, window lengths for time series etc.
Normalization is also still hugely important for many neural network problems.
Smerity says it best: http://smerity.com/articles/2016/architectures_are_the_new_f...
I'm personally quite interested to see if we find meaningful ways of constructing differentiable feature extractors that we can train conjointly with a neural net.
DNNs are really well suited to unstructured data, which isn't the kind he highlights. One reason for that is because they automatically extract features from data using optimization algorithms like stochastic gradient descent with backpropagation. What that means is they bypass the arduous process of feature engineering. They help you get around that chokepoint, so that you can deal with unstructured blobs of pixels or blobs of text.
Because unstructured data is most of the data in the world, and because DNNs excel at modeling it, they have proven to be some of the most useful and accurate algorithms we have for many problems.
Here's an overview of DNNs that goes into a bit more depth:
http://deeplearning4j.org/neuralnet-overview.html