Neural Networks
Jump to navigation
Jump to search
Frameworks
Neural Architecture Search
ENAS
- Efficient Neural Architecture Search via Parameter Sharing - Pham, H. et all 2018
- Authors' implementation of "Efficient Neural Architecture Search via Parameter Sharing" (2018) in TensorFlow
- ENAS and ProxylessENAS tutorial in AutoGluon
- "Traditional reinforcement learning-based neural architecture search learns an architecture controller by iteratively sampling the architecture and training the model to get final reward to update the controller. It is extremely expensive process due to training CNN."
- "Recent work of ENAS and ProxylessNAS construct an over-parameterized network (supernet) and share the weights across different architecture to speed up the search speed. The reward is calculated every few iterations instead of every training period."
General
- Neural Networks for Pattern Recognition - read Nikita's book.
- biological neural networks - group or groups of chemically connected or functionally associated neurons.
- synapse - connection
- artificial neural networks - made up of interconnecting artificial neurons (programming constructs that mimic the properties of biological neurons). Artificial neural networks may either be used to gain an understanding of biological neural networks, or for solving artificial intelligence problems without necessarily creating a model of a real biological system. The real, biological nervous system is highly complex and includes some features that may seem superfluous based on an understanding of artificial networks.