Implementing inference procedures for each new probabilistic model is time-consuming and error-prone. Probabilistic programming addresses this problem by allowing a user to specify the model and then automatically generating the inference procedure. To make this practical it is important to generate high performance inference code. In turn, on modern architectures, high performance requires parallel execution. In this paper we present Augur, a probabilistic modeling language and compiler for Bayesian networks designed to make effective use of data-parallel architectures such as GPUs. We show that the compiler can generate data-parallel inference code scalable to thousands of GPU cores by making use of the conditional independence relationships in the Bayesian network.

Implementing inference procedures for each new probabilistic model is timeconsuming and error-prone. Probabilistic programming addresses this problem by allowing a user to specify the model and then automatically generating the inference procedure. To make this practical it is important to generate high performance inference code. In turn, on modern architectures, high performance requires parallel execution. In this paper we present Augur, a probabilistic modeling language and compiler for Bayesian networks designed to make effective use of data-parallel architectures such as GPUs. We show that the compiler can generate data-parallel inference code scalable to thousands of GPU cores by making use of the conditional independence relationships in the Bayesian network.

Implementing inference procedures for each new probabilistic model is time-consuming and error-prone. Probabilistic programming addresses this problem by allowing a user to specify the model and then automatically generating the inference procedure. To make this practical it is important to generate high performance inference code. In turn, on modern architectures, high performance requires parallel execution. In this paper we present Augur, a probabilistic modeling language and compiler for Bayesian networks designed to make effective use of data-parallel architectures such as GPUs.

Implementing inference procedures for each new probabilistic model is timeconsuming and error-prone. Probabilistic programming addresses this problem by allowing a user to specify the model and then automatically generating the inference procedure. To make this practical it is important to generate high performance inference code. In turn, on modern architectures, high performance requires parallel execution. In this paper we present Augur, a probabilistic modeling language and compiler for Bayesian networks designed to make effective use of data-parallel architectures such as GPUs. We show that the compiler can generate data-parallel inference code scalable to thousands of GPU cores by making use of the conditional independence relationships in the Bayesian network.

Image quality remains a key problem for both traditional and deep learning (DL)-based approaches to retinal image analysis, but identifying poor quality images can be time consuming and subjective. Thus, automated methods for retinal image quality scoring (RIQS) are needed. The current state-of-the-art is MCFNet, composed of three Densenet121 backbones each operating in a different colour space. MCFNet, and the EyeQ dataset released by the same authors, was a huge step forward for RIQS. We present QuickQual, a simple approach to RIQS, consisting of a single off-the-shelf ImageNet-pretrained Densenet121 backbone plus a Support Vector Machine (SVM). QuickQual performs very well, setting a new state-of-the-art for EyeQ (Accuracy: 88.50% vs 88.00% for MCFNet; AUC: 0.9687 vs 0.9588). This suggests that RIQS can be solved with generic perceptual features learned on natural images, as opposed to requiring DL models trained on large amounts of fundus images. Additionally, we propose a Fixed Prior linearisation scheme, that converts EyeQ from a 3-way classification to a continuous logistic regression task. For this task, we present a second model, QuickQual MEga Minified Estimator (QuickQual-MEME), that consists of only 10 parameters on top of an off-the-shelf Densenet121 and can distinguish between gradable and ungradable images with an accuracy of 89.18% (AUC: 0.9537). Code and model are available on GitHub: https://github.com/justinengelmann/QuickQual . QuickQual is so lightweight, that the entire inference code (and even the parameters for QuickQual-MEME) is already contained in this paper.

In this paper we present BayesLDM, a system for Bayesian longitudinal data modeling consisting of a high-level modeling language with specific features for modeling complex multivariate time series data coupled with a compiler that can produce optimized probabilistic program code for performing inference in the specified model. BayesLDM supports modeling of Bayesian network models with a specific focus on the efficient, declarative specification of dynamic Bayesian Networks (DBNs). The BayesLDM compiler combines a model specification with inspection of available data and outputs code for performing Bayesian inference for unknown model parameters while simultaneously handling missing data. These capabilities have the potential to significantly accelerate iterative modeling workflows in domains that involve the analysis of complex longitudinal data by abstracting away the process of producing computationally efficient probabilistic inference code. We describe the BayesLDM system components, evaluate the efficiency of representation and inference optimizations and provide an illustrative example of the application of the system to analyzing heterogeneous and partially observed mobile health data.

This is the second post in the two-part series on how Tyson Foods Inc., is using computer vision applications at the edge to automate industrial processes inside their meat processing plants. In Part 1, we discussed an inventory counting application at packaging lines built with Amazon SageMaker and AWS Panorama . In this post, we discuss a vision-based anomaly detection solution at the edge for predictive maintenance of industrial equipment. Operational excellence is a key priority at Tyson Foods. Predictive maintenance is an essential asset for achieving this objective by continuously improving overall equipment effectiveness (OEE).

We faced some difficulties with Streamlit.io You can see our SageMaker implementation here. The purpose of this article is to provide a tutorial with examples showing how to deploy ML models to AWS SageMaker. This tutorial covers only deploying ML models that are not trained in SageMaker. It is more complicated to deploy your ML models that are trained outside of AWS SageMaker than training the models and deploy end-to-end within SageMaker.

Prisma Cloud from Palo Alto Networks is sponsoring our coverage of AWS re:Invent 2021. Launched at the company's re:Invent 2021 user conference earlier this month, Amazon Web Services' Amazon SageMaker Serverless Inference is a new inference option to deploy machine learning models without configuring and managing the compute infrastructure. It brings some of the attributes of serverless computing, such as scale-to-zero and consumption-based pricing. With serverless inference, SageMaker decides to launch additional instances based on the concurrency and the utilization of existing compute resources. The fundamental difference between the other mechanisms and serverless inference is how the compute infrastructure is provisioned, scaled, and managed. You don't even need to choose an instance type or define the minimum and maximum capacity.

The last decade has been phenomenal in the growth of Data Science as a discipline. Enormous strides have been made in almost all phases of data science that resulted in some of biggest innovations in recent times. As the exploration phase matures there is increasing focus on moving these data science findings into products and solutions that can be usable in market. These solutions and products needs to be reliable, resilient,scalable and most important of all, stand test of time. Software development practices have been around for more than 40 years now, and software delivery models has gone through multiple phases and has stabilized enough that more and more of our day to day activities are software driven.