50+ days of Machine Learning

 Hello :) Today is Day 151! A quick summary of today: my collaborator recorder more audio and the Scottish (Glaswegian) dataset is growing read more papers related to OD (origin-destination) matrix prediction for taxis Fristly, about the Glaswegian dataset The process of adding data to huggingface is faster now, so it is going great. We are up to ~18 mins. Secondly, about the papers from today First paper is GNN for Traffic Forecasting - A survey Problems Traffic flow Traffic flow is the number of vehicles that pass through a spatial unit, such as a road segment or traffic sensor point in a given time slot. Three types are considered: road-level, region-level and station-level. Traffic speed This is the average speed of vehicles passing through a spatial unit in a given time slot. Traffic speed problems are categorized into road-level and region-level issues, including travel time and congestion predictions. Traffic congestion prediction aids in optimizing road conditions and vehicle f

 Hello :) Today is Day 150! A quick summary of today: read a few more papers about taxi demand and Origin-Destination matrix prediction using Graph Neural Networks added more audio clips to the Scottish (Glaswegian) dataset Obisdian makes this nice graphs of papers referencing each other. First paper is  Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks (some will be pictures because I am yet to find a better way to share the math notations) Introduction Multivariate time series forecasting can learn traffic jam patterns ahead of time. However, a common challenge is capturing dynamic dependencies across multiple variables. For example the traffic on a highway can experience two patterns - daily (morning vs evening traffic) and weekly (weekday vs weekend). If a model is not able to handle complex data, then time-series forecasting is not feasible. To this end, the authors propose the usage of deep neural networks (RNN and CNN), and in particular - Long- and Short

 Hello :) Today is Day 149! A quick summary of today: back in the lab and read 2 papers about Origin-Destination Matrix Prediction via Graphs I decided to start using obsidian to take notes and it is amazing. It is also good practice writing math using latex. Also for some reason I cannot copy paste the math formulas, so some of the text below is in pictures so that the formula (math notation) can be included for clarity. I need to figure out a way to better share these notes.  Paper 1: Gallat - Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph (DDW) Introduction At first, studies concentrated on passenger demand as a function of starting location and time period. However, this failed to account for the passengers' destination. This was tackled by the definition of Origin-Destination Matrix prediction problems, where there are different time slots with their own OD matrix describing travel demand from region i to region j. Based on th

 Hello :) Today is Day 148! A quick summary of today: attended day 2 of the Microsoft Azure hackathon in the Microsoft office in Seoul Today ~ we tried. The 3rd challenge from yesterday - deploying an AI-powered chat app... well we could not do it today either. Turns out all the teams were facing the same issue and I was trying to fix errors on that 3rd task. The main issue was at the last step - deployment and people were getting some kind of os error. At some point I got that too, and after trying to fix it I started getting another error in regards to access (felt like I went a step back maybe haha). In the end ~~~ It was not possible, and the 4th challenge which was about testing the app from the 3rd challenge was not possible to complete either.  Then I moved to the 5th one. Part of it was setting up an indexer that reads documents, then setting up a model that recognizes and read different parts of invoices (pics below) Actually I realise now as I am writing that I did not take m

 Hello :) Today is Day 147! A quick summary of today: attended day 1 of Microsoft Azure hackathon The learning objectives of the hackathon: Understand GenAI concepts and how they can be used to build chat applications Learn how to configure the Azure OpenAI service and use Azure AI Search to build private OpenAI with your own data Gain practical experience in implementing a chat app architecture with Terraform Explore features of chat apps, such as multilingual queries and advanced chat response settings Apply GenAI to real-world scenarios, including increased user interactions and dynamic document processing Operationalize AI-enabled applications with enterprise-level monitoring and logging Scale AI-enabled applications with enterprise-level load balancing We are assinged to a table and the people on a table work together as a team. It is all about using Azure and its services. There are in total 6 challenges, 3 for Day 1 and the others for Day 2. Below are some pics/notes from the fi