saisurbehera Goto Github PK
Type: User
Bio: Go blue
Twitter: saisamsur
Location: Ann Arbor
Blog: saisur.info
Type: User
Bio: Go blue
Twitter: saisamsur
Location: Ann Arbor
Blog: saisur.info
The Commute behavior, Traffic Congestion, and Parking model simulates traffic moving in a simplified city grid with several perpendicular one-way streets that forms an intersection. It allows you to control global variables, such as the parking ratio and the number of people, and explore traffic dynamics, particularly traffic congestion measured by average speed and average waiting time for parking, which add to the total utility. This model gives the cars destinations (house or work) to investigate the traffic flow of commuting people. The agents in this model use goal-based and adaptive cognition. ## HOW IT WORKS Each time step, the cars face the next destination they are trying to get to (work or house) and attempt to move forward at their current speed and keep a safety speed. If their current distance to the car directly in front of them is less than their safety distance, they decelerate. If the distance is larger than safety distance, they accelerate. If there is a red light or a stopped car in front of them, they stop. In each cycle, each car will be assigned one destination. Traffic lights at the intersection will automatically change at the beginning of each cycle. Once the car parked, it will take 20 seconds to get into the front door of a company and then the car dispears from the map, at the same time a parking spot is empty for the next one. If a car driving through its destination, however the parking spot is not empty, it will keep driving around until spot opens up.
🧑🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Assignments for COMS 6998 - Practical Deep Learning Systems Performance at Columbia
A project to understand temporal embeddings. This is work in progress
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
Dreamfusion with Stable diffusion backend
code for assignment for eecs598009
FunSearch with OpenAI
This is my Homework 1
hw2
Hw4 done with the first group
hw5
Homework6 2021 SI339
homework7-2021
Implementation of "Induction of Subgoal Automata for Reinforcement Learning" (AAAI-20) and "Induction and Exploitation of Subgoal Automata for Reinforcement Learning" (JAIR).
Source code of K-BERT
Transformer based on a variant of attention that is linear complexity in respect to sequence length
Learn how to responsibly deliver value with ML.
An experimental implementation of the retrieval-enhanced language model
Repo for external large-scale work
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.