Computational epigraphy is an interdisciplinary area that combines computing and the study of ancient inscriptions. The main challenge or bottleneck faced in the field of epigraphical research is the lack of standardized corpora of the ancient scripts under study. Preparing such data from raw archaeological records, requires laborious human effort, expertise and a lot of time. Machine Learning has been used in the past to reduce human effort in epigraphical research, in problems such as classification and search for graphemic patterns. However, ML and in specific Deep Learning has not been applied yet, for the complementary task of corpus preparation. This talk will be focusing on how a deep learned pipeline architecture was designed to serve as an OCR (Optical Character Recognition) engine that is capable of reading the Indus script, one of the ancient and undeciphered inscriptions of the Harappan Civilization. This pipeline takes as input, images of the undeciphered Indus script, as found in archaeological artifacts, and returns as output a string of graphemes, suitable for inclusion in a standard corpus.
The primary focus of talk is about the performance of the system and strategies used to implement the features like partitioning, distribution, replication, prefix scans and distributed scans.
Talk would answer the following questions. 1. How are transactions handled internally in Hive? 2. How do Hive and PostgreSQL guarantee Serializable Isolation?
Networking & Dinner
Geek Night is a monthly event to promote sharing of technical knowledge and increase collaboration between geeks in Chennai. It is organized by a passionate group of programmers and sponsored by ThoughtWorks.
It happens on the Last Thursday of every month, unless that's a public holiday or any other unavoidable cause, like an Alien invasion.
We love feedback! If you have any suggestions or cribs, feel free to fill out our feedback form. Don't worry, its completely anonymous.Geek Night Volunteers