Explains how model architectures can be discovered automatically rather than hand-designed by experts, covering the search space, strategy, and performance estimation that underpin NAS — useful context for anyone thinking beyond off-the-shelf architectures.
Although most popular and successful model architectures are designed by human experts, it doesn’t mean we have explored the entire network architecture space and settled down with the best option.
We would have a better chance to find the optimal solution if we adopt a systematic and automatic way of learning high-performance model architectures.
Transcript
Although most popular and successful model architectures are designed by human experts, it doesn’t mean we have explored the entire network architecture space and settled down with the best option. We would have a better chance to find the optimal solution if we adopt a systematic and automatic way of learning high-performance model architectures.
