Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
A collection of research articles, blog posts, slides and code snippets about deep learning in applied settings. Including trained models and simple methods that can be used out of the box. Mainly focusing on Convolutional Neural Networks (CNN) but Recurrent Neural Networks (RNN), deep Q-Networks (DQN) and other interesting architectures will also be listed.
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Properties: 8 weight layers (5 convolutional and 2 fully connected), 60 million parameters, Rectified Linear Units (ReLUs), Local Response Normalization, Dropout
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Properties: 19 weight layers, 144m parameters, 3x3 convolution filters, L2 regularised, Dropout, No Local Response Normalization
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Main building block of the network:
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Features are also very good and transferable with (faster) R-CNNs (see below):
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Deep dreaming from noise:
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Top selfies according to the ConvNet:
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Applied Deep Learning Resources
Applied Deep Learning Resources
CNN
DQN
RNN
Other promising or useful architectures
Framework benchmarks
Other resources
Credits
Their summary: From our experiments, we observe that Theano and Torch are the most easily extensible frameworks. We observe that Torch is best suited for any deep architecture on CPU, followed by Theano. It also achieves the best performance on the GPU for large convolutional and fully connected networks, followed closely by Neon. Theano achieves the best performance on GPU for training and deployment of LSTM networks. Finally Caffe is the easiest for evaluating the performance of standard deep architectures.
