InferPy: Probabilistic modeling with Tensorflow made easy

Probabilistic Models with Deep Neural Networks

“…One of the main reasons for the wide adoption of deep learning has been the availability of (open-source) software tools containing robust and well-tested implementations of the main building blocks for defining and learning DNNs [ 34 , 35 ]. Recently, a new wave of software tools have appeared, building on top of these deep learning frameworks in order to accommodate modern probabilistic models containing DNNs [ 29 , 30 , 31 , 32 , 33 , 96 , 97 , 98 ]. These software tools usually fall under the umbrella term probabilistic programming languages (PPLs) [ 37 , 38 ], and support methods for learning and reasoning about complex probabilistic models.…”

“…This framework is compatible with neural networks defined with Keras [99]. • InferPy [32,33] is a Python package built on top of Edward which focuses on the ease of use. It provides a compact and simple way to code probabilistic models with DNNs, at the expense of slightly reducing expressibility and flexibility.…”

“…This new family of probabilistic models can encode objects like images, text, audio, and video probabilistically, thus bringing many of the recent advances produced by the deep learning community to the field of probabilistic modeling. The release of modern probabilistic programming languages [ 29 , 30 , 31 , 32 , 33 ] relying on well established deep learning engines like Tensorflow [ 34 ] and PyTorch [ 35 ] have also significantly contributed to the adoption of these powerful probabilistic modeling techniques.…”

InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy

“…This paper presents a new version of InferPy as a high-level Python API for probabilistic modeling with deep NNs with a strong focus on ease of use. The main differences with the previous version [5] are the following ones. Models can now contain deep NNs to model non-linear relationships among random variables.…”

Applications of artificial neural networks in three agro-environmental systems: microalgae production, nutritional characterization of soils and meteorological variables management

“…The importance of being free and open source lies in the affordability for use in academics and research. TensorFlow, one of the frameworks that most interest has caught in developers in the last few years, is developed by the Google Brain Group, part of the Google Machine Intelligence Research Institute (Qin et al, 2019), and the use of the framework is increasing research since it was released in 2015 (Abadi et al, 2016;Cabañas et al, 2019;Hazan et al, 2018;Kulkarni et al, 2018;Vázquez-Canteli et al, 2019;Zhang and Kagen, 2017).…”