Supported neural network architectures •Adaline •Perceptron •Multi Layer Perceptron with Backpropagation, Momentum on Resilient Propagation •Hopfield network •Bidirectional Associative Memory •Kohonen network •Hebbian network •Maxnet •Competitive network •Instar •Outstar •RBF network •Neuro Fuzzy Reasoner Other features •Small number of the essential base classes in core package (only 10) which can be easily reused or extended •Support for supervised and unsupervised learning rules •An easy-to-follow structure and logic. •Java & Neural Network IDE, Neuroph Studio, based on NetBeans Platform •Image recognition support •OCR support •Stock market prediction sample •Learning vizualisation samples •Data normalization •Simple microbenchmarking framework

Tight integration with NumPy – Use numpy.ndarray in Theano-compiled functions. Transparent use of a GPU – Perform data-intensive computations much faster than on a CPU. Efficient symbolic differentiation – Theano does your derivatives for functions with one or many inputs. Speed and stability optimizations – Get the right answer for log(1+x) even when x is really tiny. Ddynamic C code generation – Evaluate expressions faster. Extensive unit-testing and self-verification – Detect and diagnose many types of errors.