InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy

These can generate data samples using probabilistic constructs that include NNs. This has provoked a strong impact within the deep learning community as it allowed dealing with many unsupervised learning problems. See [2] for a recent review of these models. Along these lines, a new set of software tools have appeared, building on top of standard deep learning frameworks, in order to accommodate probabilistic models containing NNs [5, 3, 4]. These tools usually fall under the umbrella term probabilistic programming languages (PPLs) [7], and provide support for methods for reasoning about complex probabilistic models. Some examples are Edward2/TFP [8, 3], Pyro [4], etc. 3. Software Framework The main features of InferPy are: (i) Its simple API allows easy prototyping of probabilistic models including NNs; (ii) Unlike Edward2/TFP, it is not require to have a strong background in the inference methods available (Variational Inference [1, 2] and Monte Carlo methods [9]) as many details are hidden to the user; (iii) Parallelization details are also hidden to the user: InferPy runs seamlessly on CPUs and GPUs. InferPy can be seen as an upper layer for working with Edward2/TFP. Thus, models that can be defined in InferPy are those that can be defined using Edward2/TFP. InferPy is distributed as open-software (Apache-2.0)