Paper Daily: StyleGAN

by Yuan Ma

A style-Based Generator Architecture for Generative Adversarial Networks The authors propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes, and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of … Continue reading Paper Daily: StyleGAN

Paper Daily: Rethinking the value of network pruning

by Yuan Ma

In this work, the authors make several surprising observations which contradict common beliefs. Their results have several implications: 1) training a large, over-parameterized model is not necessary to obtain an efficient final model, 2) learned “important” weights of the large model are not necessarily useful for the small pruned model, 3) the pruned architecture itself, … Continue reading Paper Daily: Rethinking the value of network pruning

Optimizing C++: Optimization Patterns

by Yuan Ma

This section gathers together a few general techniques for improving performance that are so useful that they deserve specific mention. The reader may recognize some of these patterns as the core of familiar data structures, C++ language features, or hardware innovations: Precomputation — Remove computation from the hot part of the program by performing it … Continue reading Optimizing C++: Optimization Patterns

Apache Thrift architecture

by Yuan Ma

The Apache Thrift Framework can be organized into five layers: 12345* The RPC Server Library * RPC Service Stubs * User-Defined Type Serialization * The Serialization Protocol Library * The Transport Library Applications requiring a common way to serialize data structures for storage or messaging may need nothing more than the bottom three layers of … Continue reading Apache Thrift architecture

Microservice Patterns – Escaping Monolithic Hell

by Yuan Ma

Scale cube and micro-services The model defines three ways to scale an application: X, Y, and Z.  X-axis scaling X-axis scaling is a commonly to scale an application. You simple run multiple instances of the application behind a load balancer.  The load balancer distributes requests amongst the N identical instances of the application. … Continue reading Microservice Patterns – Escaping Monolithic Hell

Sequence Modeling: Recurrent and Recursive Nets

by Yuan Ma

a recurrent neural network is a neural network that is specialized fro processing a sequence of values . Just as convolutional networks can readily scale to images with large width and height, and some convolutional networks can readily sale to images with large width an height, and some convolutional networks can process images of variable … Continue reading Sequence Modeling: Recurrent and Recursive Nets

Autonomous Driving: Modeling and Learning Behaviors

by Yuan Ma

Motion planning for dynamic environments is clearly one of the main problems that needs to be solved for effective autonomous navigation. As shown by Ref and Sharir, the general problem is NP-Hard, which explains the continued efforts to find algorithms to cope with that complexity. A much more overlooked but equally critical aspect of the … Continue reading Autonomous Driving: Modeling and Learning Behaviors

Mastering CMake — Key Concepts

by Yuan Ma

Key Concepts Main Structures This chapter provides an introduction not CMake's key concepts. As you start working with CMake, you. Will run into a variety of concepts such as targets, generators, and commands. In CMake, these concepts are implemented as C++ classes and are referenced in many of CMake's commands. Understanding these concepts will provide … Continue reading Mastering CMake — Key Concepts

Autonomous Driving: Context and the State-of-the-Art

by Yuan Ma

In this section the state-of-the-art in Intelligent Vehicles will be presented from a vehicle navigation perspective as these achieve autonomous navigation capabilities. The section is structured as follows: Motivation: The motivation to this ongoing transformation of modern vehicles are presented in terms of usage, safety and external factors such as fossil-fuel constraints, pollution. Vehicle navigation … Continue reading Autonomous Driving: Context and the State-of-the-Art