Graph Convolutional Neural Networks for Web-Scale Recommender Systems — So finally Pinterest has deployed PinSage as their recommender system and everyone is really excited about the change and the shift in paradigm. But what is it really and how is it related to GraphSAGE? If we look at PinSage title it reads as follows Graph Convolutional Neural Networks for…

Implementing Neural Networks and checking how the accuracy changes upon the change of parameters find the code here. Question 1 Self-Implemented NN: Accuracy:

This blog is about the results and observations of the works in Decision Tree and Random Forest. Click here to check the code and the problem statement. Part A:

Table of Contents: What is TF-IDF? Preprocessing data. Weights to title and body. Document retrieval using TF-IDF matching score. Document retrieval using TF-IDF cosine similarity. Introduction: TF-IDF TF-IDF stands for “Term Frequency — Inverse Document Frequency”. This is a technique to quantify words in a set of documents. We generally compute a score for each…

This is a series on Information Retrieval techniques with implementation basic concepts and easily understandable examples. For those who are highly interested, i suggest the book “Introduction to Information Retrieval” book by Manning Click here to checkout the git repo. Information Retrieval Series: 1. Introduction 2. Unigram Indexing & Positional Indexing 3. TF-IDF …

Code: GitRepo Hyperparameters Used: - Learning Rate - Discount Rate - Exploration Rate Learning Rate [0, 1]: Learning rate is the rate of learning or the amount of information that we are taking from the current iteration into the Q-table. Discount Rate [0, 1]: Discount rate is the amount of…

Code: GitRepo Assumptions: - Termination condition is assumed to be “similarity of path taken by all the ants” - The count of ants is taken as twice the count of cities, by default - Other than these, ACO is implement as per the algorithm - Alpha is the influence on…

Code: GitRepo Genetic Algorithm (GA) - There is always a sub-optimal solution during the generations in GA and MA. We need not wait for thousands of years just to get to the optimal answer. - All the timetable algorithms and constraints are developed considering the IIITD timetable and the staff and lecture halls…

Code: GitHub Minimax Minimax is an algorithm which can never lose. Basically what happens here is that it increases its chances of winning and minimises the opponent’s chances of winning. Max → Min Min → Max Max will call min and min will call max recursively. This basically forms a game…