Interesting work on reviving RNNs. https://t.co/kTOze8qINv -- in general the fact that there are many recent architectures coming from different directions that roughly match Transformers is proof that architectures aren't fundamentally important in the curve-fitting paradigm (aka deep learning)
Curve-fitting is about embedding a dataset on a curve. The critical factor is the dataset, not the specific hard-coded bells and whistles that constrain the curve's shape. As long as your curve is sufficiently expressive all architectures will converge to the same performance in the large-data regime.
What if Germany had invested in nuclear power? A comparison between the German energy policy the last 20 years and an alternative policy of investing in nuclear power https://t.co/KYgVJCL8kJ
Starting out with microservices is probably almost always the wrong decision, because it is primarily an organizational issue. Except when the scaling is needed right off the bat. But even then ... https://t.co/ejGV18zLuh