A Comparative Study of Process Mining Tools: FlexFringe, ProM, MINT and PRINS

Nowadays, software is an integral part of many companies. However, the codebase can grow large and complicated and is often insufficiently documented. To gain insight, tools have been made to infer state machines and process models from software logs. These tools produce different types of models such as automata and Petri nets. The main...

A Survey on Accelerating Sparse CNN Inference on GPUs

Convolutional neural networks (CNNs) are often pruned to achieve faster training and inference speed while also requiring less memory. Nevertheless, during computation, most modern GPUs cannot take advantage of the sparsity automatically, especially on networks with unstructured sparsity. Therefore, many libraries that exploit sparsity, have...

Hybrid Posit and Fixed Point Hardware for Quantized DNN Inference

The recently introduced posit number system was designed as a replacement for IEEE 754 floating point, to alleviate some of its shortcomings. As the number distribution of posits is similar to the data distributions in deep neural networks (DNNs), posits offer a good alternative to fixed point numbers in DNNs: using posits can result in high...

Integration of a convolutional neural network for speech-to-text recognition in an FPGA compiler flow

Deep Neural Network (DNNs) have increased significantly in size over the past decade. Partly due to this, the accuracy of DNNs in image classification and speech recognition tasks has increased as well. This enables a great potential for such models to be applied in real-world applications. However, due to their size, the compute and power...

Analysis of Loading Policies for Multi-model Inference on the Edge

The increasingly growing expansion of the Internet of Things (IoT) along with the convergence of multiple technologies such as the arrival of next generation wireless broadband in 5G, is creating a paradigm shift from cloud computing towards edge computing. Performing tasks normally done by the cloud directly on edge devices would ensure...

Modeling Inference Time of Deep Neural Networks on Memory-constrained Systems

Deep neural networks have revolutionized multiple fields within computer science. It is important to have a comprehensive understanding of the memory requirements and performance of deep networks on low-resource systems. While there have been efforts to this end, the effects of severe memory limits and heavy swapping are understudied. We have...

Probabilistic partial least squares model: Identifiability, estimation and application

With a rapid increase in volume and complexity of data sets, there is a need for methods that can extract useful information, for example the relationship between two data sets measured for the same persons. The Partial Least Squares (PLS) method can be used for this dimension reduction task. Within life sciences, results across studies are...

Handleiding voor het gebruik van NEXT 1.2 - User manual NEXT 1.2 - NLR engineering X-pert system Toolkit

NEXT 1.2 is an expert system shell developed at NLR. NEXT has a knowledge representation mechanism based on a combination of context tree and production rules. The inference mechanism is based on a combination of backward and forward reasoning. NEXT 1.2 is available on a CYBER 180/855 under NOS and on a VAX under VMS. Supply of other...