SLAM
Project Overview:
The aim of this project is to implement SLAM (Simultaneous Localization and Mapping) for a two dimensional world. Based on the map of the environment created, the location of the robot is tracked and the locations of the landmarks such as buildings are identified in the real time.
Image Source: [ Google ]
IMAGE CAPTIONING
Project Overview:
The aim of this project is to construct a neural network architecture (CNN Encoder- RNN Decoder) which generates captions from images (text describing the image) automatically. The model is trained on Microsoft Common Objects in Context (MS COCO) dataset and the network is tested on the novel images.
Image Source: [ Google ]
QUORA - IDENTIFYING QUESTIONS WITH SAME INTENT
Project Overview:
The goal is to build a binary classification model using a simulated dataset containing a pair of questions and a binary class label stating whether a pair is duplicate or not. In this project, I will be handling this problem by applying advanced techniques (Random Forest, K-Means, SVM, XGBoost etc.) to classify whether question pairs are duplicates or not. After applying several models, I’ll be comparing the accuracy obtained with each model. Doing so will make it easier to find high quality answers to questions resulting in an improved experience for Quora writers, seekers, and readers.
Image Source: [Google ]
FACIAL KEYPOINTS DETECTION
Project Overview:
Facial Keypoints Detection is one of the trending topics these days. Its applications include facial tracking, facial pose recognition, facial filters, and emotion recognition.
In this project, the knowledge of computer vision techniques and deep learning architectures is combined to build a facial keypoint detection system (identifying 68 facial keypoints). Facial keypoints include points around the eyes, nose, and mouth on a face.
To tackle this problem, a convolutional neural network is trained to perform facial keypoint detection, and computer vision techniques are used to transform images of faces.
Image Source: [ Google]
SMART CAB
Project Overview:
In this project reinforcement learning techniques are applied for a self-driving agent in a simplified world to aid it in effectively reaching its destinations in the allotted time.
Image Source: [ Google ]
IMAGE CLASSIFICATION
Project Overview:
The aim of this project is to build a convulational neural network using Tensorflow which classifies images from the CIFAR-10 dataset. The dataset consists of airplanes, dogs, cats, and other objects.
To summarize, the images in the dataset are preprocessed, and then a convolutional neural network is trained on all the samples. The images need to be normalized and the labels need to be one-hot encoded. A convolutional, max pooling, dropout, and fully connected layers are built and then at the end, neural network's predictions on the sample images are examined.
To read more about CNNs, follow this blog
Image Source: [ Google]
NYC SUBWAY DATA ANALYSIS
Project Overview:
The aim of this project is to analyze the NYC Subway Data to find out whether more people ride the subway when it’s raining versus when it’s not.
New York City Subway data is compared and statistical methods and data visualization techniques are used to draw an interesting conclusion about the subway with the dataset that is analyzed.
The primary goal of this project is to explore the relationship between data from the NYC Subway turnstiles and the city weather.
Image Source: [ Google ]
CUSTOMER SEGMENTS
Project Overview:
In this project unsupervised learning techniques are applied on product spending data collected for customers of a wholesale distributor in Lisbon, Portugal to identify customer segments hidden in the data.
Image Source: [Google ]
FINDING CHARITY DONOR
Project Overview:
This project is aimed at performing analysis and developing certain supervised learning techniques on the data collected for the U.S. census to help a certain organisation identify people most likely to sonate to their cause.
Image Source: [ Google]
HOUSE PRICE PREDICTION
Project Overview:
The main of the project is to apply basic machine learning concepts on the data collected for housing prices in the Boston, to predict the selling price of a new home.
Image Source: [ Google ]
TITANIC SURVIVAL EXPLORATION
Project Overview:
This project is aimed at creating decision functions that attempt to predict survival outcomes from the 1912 Titanic disaster based on each passenger's features. Basically, a subset of the RMS Titanic passenger manifest is explored to determine which features best predict whether someone survived or did not survive.
SMS SPAM CLASSIFICATION
Project Overview:
The aim of the project is to classify the messages into ‘Spam’ and ‘Ham’ categories.
