StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks

The computational complexity of leveraging deep neural networks for extracting deep feature representations is a significant barrier to its widespread adoption, particularly for use in embedded devices. One particularly promising strategy to addressing the complexity issue is the notion of evolutionary synthesis of deep neural networks, which was demonstrated to successfully produce highly efficient deep neural networks while retaining modeling performance... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Global Average Pooling
Pooling Operations
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Convolution
Convolutions
Darknet-19
Convolutional Neural Networks
Local Response Normalization
Normalization
Grouped Convolution
Convolutions
ReLU
Activation Functions
Dropout
Regularization
Dense Connections
Feedforward Networks
Max Pooling
Pooling Operations
Softmax
Output Functions
YOLOv2
Object Detection Models
AlexNet
Convolutional Neural Networks