- Various types of artificial neural networks: multilayer neural network, convolutional neural network (CNN) with convolutional layers, subsampling layers and max-pooling layers, random projections for data and network compression and extreme learning machines, restricted Boltzmann machines (RBM) and sparse auto-encoders (SAE) for unsupervised pretraining
- Optimization algorithms: mini-batch stochastic gradient descent (MBSGD) for large networks, conjugate gradient (CG) for large networks, limited memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) and Levenberg-Marquardt algorithm (LMA) for smaller networks, (increasing population size) covariance matrix adaption evolution strategies (IPOPCMAES) for reinforcement learning
- Supported languages: C++, Python bindings
- Changes to previous version:
- L-BFGS optimizer
- sparse auto-encoder
- preprocessing: normalization, PCA, ZCA whitening
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.