-
Iguazio + Nuclio를 활용한 실시간 추천시스템 구축
Iguazio
-
Principal pattern recognition on unsupervised learning
● Principal Pattern Recognition 이란 Log Data의 행들간의 거리값을 기반으로 군집화하여 가장 주요패턴그룹을 인지한다. ● 목적 샘플링 1000건에서 일반화된 하나의 AD Language를 생성한다. 그런데 샘플 1000건중에 오류 데이터가 있으면 그 특성까지 반영되어 버림에 따라 샘플 1000건 중에 주요 패턴 그룹을 찾아 이를 기반으로 일반화 하여 AD Language의 품질을 높인다. ● 행들간 거리 값 산출 공식 Log Data를 수치로 변환하기 위해 아래와 같은 공식으로 행들간의 거리값을 계산하여, 클러스터링 입력파라메타로 활용한다. ※ 위 결과값은 ‘0’과 ‘1’사이의 값을...
-
Nuclio is Serverless Engine
Architecture Function processors Function processors provide an environment for executing functions. The processor feeds functions with events, provides context and data, collects logs and statistics, and manages the function’s life cycle. Processors can be compiled into a single binary (when using Go or C), or packaged into a container with all the required code dependencies. Processor containers can run as standalone Docker containers, or on top of a container-orchestration platform such as Kubernetes. Each function...
-
Iguazio is Unified Data Platform
Serverless Platform Iguazio combines real-time actions and AI across a variety of data sources and types, without compromising simplicity and fast time to market. The Iguazio platform includes leading open source data science tools, managed serverless functions and data services running on Kubernetes and on a real-time unified database. Open Platform for Intelligent Apps Faster Dev & Ops Accelerate time from data science exploration to production in a fully managed serverless environment with real-time functions,...
-
Self-Driving Car Engineer Advanced Lane Finding
Self-Driving Car Engineer Nanodegree Program Advanced Lane Finding Project The goals / steps of this project are the following: Compute the camera calibration matrix and distortion coefficients given a set of chessboard images. Apply a distortion correction to raw images. Use color transforms, gradients, etc., to create a thresholded binary image. Apply a perspective transform to rectify binary image (“birds-eye view”). Detect lane pixels and fit to find the lane boundary. Determine the curvature of...