50+ days of Machine Learning

 Hello :) Today is Day 155! A quick summary of today: Real-time Prediction of Taxi Demand Using Recurrent Neural Networks Graph WaveNet for Deep Spatial-Temporal Graph Modeling GMAN: A Graph Multi-Attention Network for Traffic Prediction DNN-Based Prediction Model for Spatio-Temporal Data The updated graph with reference connections from Obisdian is: Real-time Prediction of Taxi Demand Using Recurrent Neural Networks Introduction This paper proposes a real-time method for predicting taxi demands in different areas of a city. A big city is divided into smaller areas and during a pre-set period of time, the number of taxi requests in each area is aggregated. This way taxi data becomes a sequence and a LSTM is applied. LSTM is capable of learning long-term dependencies by utilising some gating mechanisms to store information. Therefore, it can for instance remember how many people have requested taxis to attend a concert and after a couple of hours use this information to predict that...

 Hello :) Today is Day 154! A quick summary of today: STGCN - Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting CACRNN - Predicting taxi demands via an attention-based convolutional recurrent neural network Thanks to a lab mate, I found a way to sync my Obsidian notes using google drive. So I don't need to use github anymore! But still I have to upload text with math notations as pictures.   Frist paper, STGCN Introduction The paper presents methods to effectively capture the temporal and spatial patterns in traffic flow. Instead of viewing the traffic network as separate grids or segments, it represents it as a general graph to better leverage spatial data. To address the shortcomings of recurrent networks, a fully convolutional structure along the time axis is used. The key contribution is the development of a novel deep learning model, called spatio-temporal graph convolutional networks, specifically designed for traffic ...