This article explores a very interesting paper to optimize the design space of a neural architecture search! This design space is responsible for the collection of all possible networks found in the query. By limiting this space, we save calculations and produce better networks!
Thanks for watching, subscribe!

Paper links:
Designing Network Design Spaces: https://arxiv.org/pdf/2003.13678.pdf
AlexNet: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
ResNet: https://arxiv.org/pdf/1512.03385.pdf
DenseNet: https://arxiv.org/pdf/1608.06993.pdf
The evolved transformer: https://arxiv.org/pdf/1901.11117.pdf
Hierarchical Neural Architecture Search: https://arxiv.org/pdf/1711.00436.pdf
AutoML-Zero: https://arxiv.org/pdf/2003.03384.pdf
CLOSER: https://arxiv.org/pdf/2003.08536.pdf

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.