Year: 2021

Are you still believing that Machine Learning (ML) tasks infused with Artificial Intelligence (AI) are still time-consuming, tedious and inefficient? Join this session to find out how to develop image recognition from scratch, how to use the drag-and-drop feature to complete an AI development easily, and how to improve your work efficiency as a professional…

I left Hong Kong, the place that I was born and lived for 30 years, 5 years ago with no technical experience. (Except for a few programming experience in University time, mainly serves my research studies) Moving to London, a city where technology is in high demand, opens a lot of doors for me. Here…

Under COVID, “genome” is no longer an alien word to us. Yet, there is many miles more to go to truly understand the genome as a whole set of heriditary materials, even for academic biologists. A genome sequence assembly is a collection of DNA sequences, which serves as a fundamental resource of any genetic studies,…

It is more fun to have a GUI to play with sensors than using a command line! In this session, we will discuss how to use Python to communicate with sensors on Raspberry Pi, and hence display on a GUI built with PySide2 and Qt Quick. Speaker: Mr. Arnold Chan / Hong Kong – GitHub,…

Financial data forecasting has historically been a significant domain with a wide array of consequences and applications. In today’s tech driven era, it has facilitated the prevalence of data-driven decision making, reduced uncertainties in the financial arena and propelled monetary profits unprecedentedly. Numerous techno-social algorithms and technologies have been employed to facilitate financial data forecasting….

There is generally a gap between data science practitioners who create machine learning models and the engineering/devops teams and processes that put those models into production. This often leads to data scientists not having efficient development cycles to properly test and extend the models before they make it to production, as well as limiting the…

講者將分享他在Mozilla Common Voice 廣東話數據庫中自肥的經過與發現。 講者對影像分析向來有研究，但對於語音識別及語言學一竅不通，只是對暴龍哥口音及譚仔口音略有研究。作為一個語音識別初學者，講者嘗試利用 Mozilla Common Voice 廣東話語音數據庫及 Python，訓練 AI model 去做語音識別。過程中發現各種問題，講者會試從數據使用者/程式開發員的角度，去分析廣東話語音數據庫的現狀，挑戰及機遇。最後，希望探討在有限資源下，如何「補完」香港廣東話語音數據。 計劃仍在努力中，暫時估計有以下內容： 廣東話發音的基本原理 Mozilla Common Voice Project 的基本原理 廣東話語數據庫的挑戰：英語 VS 廣東話大不同，版權，男女比例，口音，粗口， 發音覆蓋率，中英夾雜，有音無字，etc. 試用 python 訓練 AI model 做語音識別 如何「補完」數據庫? Slides：https://github.com/scottykwok/cantonese-selfish-project Speaker: Mr. Scotty Kwok / Hong Kong / Sebit Company Limited – Website, GitHub, Twitter, LinkedIn, FacebookLanguage: CantoneseDate and Time : October 9,…

Abstract Neural Prophet, a new framework that extends on the original prophet framework, addresses pain points such as scale, customization and extensibility.it incorporates traditional statistical and neural network models for time series modeling, used in forecasting and anomaly detection. Description The best thing is you can get started easily using Neural Prophet. Neural Prophet is…

Pandas is a well-known library for data scientist yet it does not scale. Koalas provides a pandas interface for big data manipulation in spark environment. In this session, koalas usage will be demonstrated for distributed data frame manipulation. Speaker: Mr. Wong Ho Wa / Hong Kong – GitHub, Twitter, LinkedInLanguage: CantoneseDate and Time : October…

The talk introduces users to state of the art deep learning model Transformer with PyTorch and use the model for small datasets that they may have Speaker: Ms. Winnie Yeung / Hong Kong / Visa – GitHubLanguage: CantoneseDate and Time : October 9, 2021 / 11:15-11:45 (UTC+8) Speaker Introduction Winnie is a senior data scientist…