ztonege Goto Github PK

10-301-intro-to-ml

All ML assignments for 10301

10-601

A repository containing solutions to homework assignments for cmu 10-601 (2018)

10-605_cifar100

Course project of 10-605 Machine Learning with Large Datasets

10601-18fall-homework

My homework solutions for CMU Machine Learning Course (10-601 2018Fall)

10601-course-projects

My course homeworks in 10601 at CMU

10601-introduction-to-machine-learning

Homework solutions for 10-601: Introduction to Machine Learning at Carnegie Mellon University, Fall 2019.

10601-machine-learning

Machine Learning Course CMU

10605-hw

10605-mini

10605 mini project

10605-ml-with-large-datasets

10605-msd-group7

Million Song Dataset Recommendations

10605courseproject

Course Project for 10-605 Machine Learning with Large Datasets.

10605proj

10605 Project

10805-mp

Mini Project A/B for 10-805: Machine Learning for Large Datasets

10805-yelpchallenge

CMU 10-805 Final Project / Yelp Challenge/ 2017 Fall / Personalized Reviews Evaluation and Ranking for Yelp Users

16-720b-computer-vision

16-720B Computer Vision (Fall 2018) at Carnegie Mellon University

16-833_slam

16720-computer-vision

This repository contains all the assignments for the computer vision class 16720 A at Carnegie Mellon University

16720-computervision

This repository contains the code for all the assignments completed as a part of the Computer Vision class at Carnegie Mellon University

16824

Visual learning courseworks in CMU

16833

Localization and Mapping Course 16833

16833-slam

16833-slam-1

16833_hw1

16833_locatization_and_mapping

Robot localization and mapping are fundamental capabilities for mobile robots operating in the real world.Even more challenging than these individual problems is their combination: simultaneous localization andmapping (SLAM). Robust and scalable solutions are needed that can handle the uncertainty inherent in sen-sor measurements, while providing localization and map estimates in real-time.

16833_particlefilter

adversarial_image_defenses

Countering Adversarial Image using Input Transformations.

afartoolbox

AFAR: A Deep Learning Based Toolbox for Automated Facial Affect Recognition

automl

AutoML is a distributed machine learning pipeline designed to scale to large datasets. AutoML aims to automate the entire process of solving a classification problem. It just requires the dataset and the target column as an input and then the system takes care of the rest. Efficient cleaning of the dataset is performed, which imputes all the missing values and gives better structure to the dataset. The system is capable of detecting categorical values, thus performing One-Hot Encoding where required. Further, in the preprocessing stage, it also takes care of feature engineering, dimensionality reduction, sampling and removal of outliers which affect the accuracy of the model. After the preprocessing stage, the ready data is trained on several models, with multiple different hyperparameters. The output of the system is the name, accuracy and code of the best model, which is judged based on its accuracy. The system is tested on over 30 datasets, both binary and multi-class classification and there is a robust system to quickly train any dataset given to it.

big_data

Works from Machine Learning with Large Datasets (10605)