It's now over a year and three months since my great father, my great dad went.

 It took me a long time to post here since my great father, my great dad, Fred Patrick Zeere Wanziguya, transitioned to the great beyond. It was the morning of 31st August 2022, just almost a week after his 75th Birthday. I can only thank God for blessing us with his life, and pray that we can have just a little of that blessing to grace us through this world till we meet again. He is currently survived by his dear wife Irene Wanziguya, his children he loved a lot, and his grandchildren he seriously enjoyed being with. There are things I thought were easy to do because he made it look easy when doing them; I have tried some of them and now really appreciate the very special kind of person he was to achieve them. Importantly, he did his bit to prepare me, and I draw significant benefits from some special and humble life values he ensured I should know and apply. Thank you, Father, Thank you, Dad.

Activities during COVID 19 Lockdown

Self-motivated research papers

I recently started investigating classification techniques on a Ugandan credit risk data set. Last year (2019) I presented some classification results form several machine learning methods. This year, I have focused on Bayesian networks and during the CoVID 19 lockdown, I forwarded my results for review.

I have also revised one of my papers on Machine Translation for one of the under-resourced languages in Uganda (Lumasaaba). Thanks to Google's colaboratory platform (colab.research.google.com), I was able to explore several Neural Machine Translation architectures. Although I had to pay for more Google Drive space to accomodate the huge resulting NMT models. I have forwarded my results for review.

Another Baby!

On Tuesday 28th August 2018 at around 5:00pm, our daughter came to this world! Thank God for everything and for Joyce!

Uganda's Mothers' index

Having been blessed with a baby born in Uganda one month ago, i took time to go through some statistics concerning Uganda's maternal status. The figures are really alarming and a successful birth in Uganda and several African countries is surely by God's grace.

Lifetime risk of maternal death: 1 in 44
Under-5 mortality rate (per 1,000 live births): 66.1
Expected number of years of formal schooling: 9.8
Gross national income per capita: 550 US $
Mother's index rank: 141/179

These should not be taken for granted! Developing countries have to address this seriously. Why would someone risk their life after taking into consideration these numbers? No wonder our leader's descendants have to be born elsewhere! No No No and No. God bless us.

Source: Save the Children Website

A Baby!

I should have posted this earlier. On Tuesday 7th 2015 (a day after Easter Monday) at around 1:00pm our son Ethan Nabende came to this world! Thank God for everything and for Joyce!

Data mining specialization on coursera

I am currently pursuing a data mining specialization on coursera.
I have utilized the first module for my data mining and datawarehousing class; i have played role of tutorial assistant and i recommend it to any one. i should be through with two modules soon.

on Statistical Machine Translation

Statistical Machine Translation is one of my main research interests. To that end, I achieved the rite of passage through the MOSES Phrase-based statistical machine translation software setup. which means that i can use Moses software to build a French to English translation system. I am now aiming to construct statistical translation systems based on MOSES that can be used to translate between Ugandan languages and English. There is already reasonable progress concerning Luganda -> English (not by me). Before anything can be done for other languages, huge amounts of parallel sentences (translations between two languages) are needed that can be used to start constructing translation models that can be used to produce reasonable translations. To sum it all, parallel sentences are very important for statistical machine translation; for languages that are yet to be looked at, language -specific software for pre-processing the sentences before they are used to build translation models are  very critical.