Difference between revisions of "F18-STAT841-Proposal"

From statwiki
Jump to: navigation, search
Line 88: Line 88:
 
Snaith, Mitchell
 
Snaith, Mitchell
  
'''Title:'''  Reproducibility report: *Variance Networks: When Expectation Does Not Meet Your Expectations*
+
'''Title:'''  Exploring Kuzushiji-MNIST, a new classification benchmark
  
 
'''Description:'''   
 
'''Description:'''   
  
The paper *Variance Networks: When Expectation Does Not Meet Your Expectations* presents a new kind of stochastic layer for neural networks called a variance layer. These variance layers have zero mean and are only parameterized by their variance. The author claims that these layers have several useful applications.  
+
The paper *Deep Learning for Classical Japanese Literature* presents a new classification dataset intended to act as a drop-in replacement for MNIST. The paper authors believe that this dataset is significantly more difficult that MNIST for typical classification methods, while not "capping" performance due to indiscernible objects like Fashion-MNIST might.  
 
Goals are to:  
 
Goals are to:  
  
- reproduce the variance layer in Pytorch, and subsequently the classification results from the paper
+
- perform survey of typical machine-learning algorithms on Kuzushiji-MNIST compared to both MNIST and Fashion-MNIST
  
- investigate which layers in particular should be variance layers to see maximum benefits
+
- investigate relevant differences in the structures of the datasets
 +
 
 +
- assess whether Fashion-MNIST does indeed seem to have a performance cap that can be overcome with Kuzushiji-MNIST
 
--------------------------------------------------------------------
 
--------------------------------------------------------------------
  

Revision as of 16:07, 9 December 2018

Use this format (Don’t remove Project 0)

Project # 0 Group members:

Last name, First name

Last name, First name

Last name, First name

Last name, First name

Title: Making a String Telephone

Description: We use paper cups to make a string phone and talk with friends while learning about sound waves with this science project. (Explain your project in one or two paragraphs).


Project # 1 Group members:

Weng, Jiacheng

Li, Keqi

Qian, Yi

Liu, Bomeng

Title: RSNA Pneumonia Detection Challenge

Description:

Our team’s project is the RSNA Pneumonia Detection Challenge from Kaggle competition. The primary goal of this project is to develop a machine learning tool to detect patients with pneumonia based on their chest radiographs (CXR).

Pneumonia is an infection that inflames the air sacs in human lungs which has symptoms such as chest pain, cough, and fever [1]. Pneumonia can be very dangerous especially to infants and elders. In 2015, 920,000 children under the age of 5 died from this disease [2]. Due to its fatality to children, diagnosing pneumonia has a high order. A common method of diagnosing pneumonia is to obtain patients’ chest radiograph (CXR) which is a gray-scale scan image of patients’ chests using x-ray. The infected region due to pneumonia usually shows as an area or areas of increased opacity [3] on CXR. However, many other factors can also contribute to increase in opacity on CXR which makes the diagnose very challenging. The diagnose also requires highly-skilled clinicians and a lot of time of CXR screening. The Radiological Society of North America (RSNA®) sees the opportunity of using machine learning to potentially accelerate the initial CXR screening process.

For the scope of this project, our team plans to contribute to solving this problem by applying our machine learning knowledge in image processing and classification. Team members are going to apply techniques that include, but are not limited to: logistic regression, random forest, SVM, kNN, CNN, etc., in order to successfully detect CXRs with pneumonia.


[1] (Accessed 2018, Oct. 4). Pneumonia [Online]. MAYO CLINIC. Available from: https://www.mayoclinic.org/diseases-conditions/pneumonia/symptoms-causes/syc-20354204 [2] (Accessed 2018, Oct. 4). RSNA Pneumonia Detection Challenge [Online]. Kaggle. Available from: https://www.kaggle.com/c/rsna-pneumonia-detection-challenge [3] Franquet T. Imaging of community-acquired pneumonia. J Thorac Imaging 2018 (epub ahead of print). PMID 30036297


Project # 2 Group members:

Hou, Zhaoran

Zhang, Chi

Title:

Description:


Project # 3 Group members:

Hanzhen Yang

Jing Pu Sun

Ganyuan Xuan

Yu Su

Title: Kaggle Challenge: Quick, Draw! Doodle Recognition Challenge

Description:

Our team chose the Quick, Draw! Doodle Recognition Challenge from the Kaggle Competition. The goal of the competition is to build an image recognition tool that can classify hand-drawn doodles into one of the 340 categories.

The main challenge of the project remains in the training set being very noisy. Hand-drawn artwork may deviate substantially from the actual object, and is almost definitively different from person to person. Mislabeled images also present a problem since they will create outlier points when we train our models.

We plan on learning more about some of the currently mature image recognition algorithms to inspire and develop our own model.


Project # 4 Group members:

Snaith, Mitchell

Title: Exploring Kuzushiji-MNIST, a new classification benchmark

Description:

The paper *Deep Learning for Classical Japanese Literature* presents a new classification dataset intended to act as a drop-in replacement for MNIST. The paper authors believe that this dataset is significantly more difficult that MNIST for typical classification methods, while not "capping" performance due to indiscernible objects like Fashion-MNIST might. Goals are to:

- perform survey of typical machine-learning algorithms on Kuzushiji-MNIST compared to both MNIST and Fashion-MNIST

- investigate relevant differences in the structures of the datasets

- assess whether Fashion-MNIST does indeed seem to have a performance cap that can be overcome with Kuzushiji-MNIST


Project # 5 Group members:

Rebecca, Chen

Susan,

Mike, Li

Ted, Wang

Title: Kaggle Challenge: Quick, Draw! Doodle Recognition Challenge

Description:

Classification has become a more and more eye-catching, especially with the rise of machine learning in these years. Our team is particularly interested in machine learning algorithms that optimize some specific type image classification.

In this project, we will dig into base classifiers we learnt from the class and try to cook them together to find an optimal solution for a certain type images dataset. Currently, we are looking into a dataset from Kaggle: Quick, Draw! Doodle Recognition Challenge. The dataset in this competition contains 50M drawings among 340 categories and is the subset of the world’s largest doodling dataset and the doodling dataset is updating by real drawing game players. Anyone can contribution by joining it! (quickdraw.withgoogle.com).

For us, as machine learning students, we are more eager to help getting a better classification method. By “better”, we mean find a balance between simplify and accuracy. We will start with neural network via different activation functions in each layer and we will also combine base classifiers with bagging, random forest, boosting for ensemble learning. Also, we will try to regulate our parameters to avoid overfitting in training dataset. Last, we will summary features of this type image dataset, formulate our solutions and standardize our steps to solve this kind problems

Hopefully, we can not only finish our project successfully, but also make a little contribution to machine learning research field.


Project # 6 Group members:

Ngo, Jameson

Xu, Amy

Title: Kaggle Challenge: PLAsTiCC Astronomical Classification

Description:

We will participate in the PLAsTiCC Astronomical Classification competition featured on Kaggle. We will explore how possible it is classify astronomical bodies based on various factors such as brightness.

These bodies will vary in time and size. Some are unknown! There are over 100 classes that these bodies may be and it will be our job to find the predicted probability for an image to be each class.


Project # 7 Group members:

Qianying Zhao

Hui Huang

Meiyu Zhou

Gezhou Zhang

Title: Quora Insincere Questions Classification

Description: Our group will participate in the featured Kaggle competition of Quora Insincere Questions Classification. For this competition, we should predict wether a question asked on Quora is sincere or not. If the question is insincere, it intends to be a statement rather than look for useful answers, and identified as (target = 1). We will analyze the Quora question text to predict the characteristics of questions and define they are sincere or insincere using Rstudio. Our presentation report will include not only how we've concluded by classifying and analyzing provided data with appropriate models, but also how we performed in the contest.


Project # 8 Group members:

Jiayue Zhang

Lingyun Yi

Rongrong Su

Siao Chen


Title: Kaggle--Two Sigma: Using News to Predict Stock Movements


Description: Stock price is affected by the news to some extent. What is the news influence on stock price and what is the predicted power of the news? What we are going to do is to use the content of news to predict the tendency of stock price. We will mine the data, finding the useful information behind the big data. As the result we will predict the stock price performance when market faces news.



Project # 9 Group members:

Hassan, Ahmad Nayar

McLellan, Isaac

Brewster, Kristi

Melek, Marina Medhat Rassmi


Title: Kaggle Compeition: Quora Insincere Questions Classification

Description:



Project # 10 Group members:

Lam, Amanda

Huang, Xiaoran

Chu, Qi

Sang, Di

Title: Kaggle Competition: Human Protein Atlas Image Classification

Description:


Project # 11 Group members:

Bobichon, Philomene

Maheshwari, Aditya

An, Zepeng

Stranc, Colin

Title: Kaggle Challenge: Quick, Draw! Doodle Recognition Challenge

Description:


Project # 12 Group members:

Huo, Qingxi

Yang, Yanmin

Cai, Yuanjing

Wang, Jiaqi

Title:

Description:


Project # 13 Group members:

Ross, Brendan

Barenboim, Jon

Lin, Junqiao

Bootsma, James

Title: Expanding Neural Netwrok

Description: The goal of our project is to create an expanding neural network algorithm which starts off by training a small neural network then expands it to a larger one. We hypothesize that with the proper expansion method we could decrease training time and prevent overfitting. The method we wish to explore is to link together input dimensions based on covariance. Then when the neural network reaches convergence we create a larger neural network without the links between dimensions and using starting values from the smaller neural network.


Project # 14 Group members:

Schneider, Jason

Walton, Jordyn

Abbas, Zahraa

Na, Andrew

Title: Application of ML Classification to Cancer Identification

Description: The application of machine learning to cancer classification based on gene expression is a topic of great interest to physicians and biostatisticians alike. We would like to work on this for our final project to encourage the application of proven ML techniques to improve accuracy of cancer classification and diagnosis. In this project, we will use the dataset from Golub et al. [1] which contains data on gene expression on tumour biopsies to train a model and classify healthy individuals and individuals who have cancer.

One challenge we may face pertains to the way that the data was collected. Some parts of the dataset have thousands of features (which each represent a quantitative measure of the expression of a certain gene) but as few as twenty samples. We propose some ways to mitigate the impact of this; including the use of PCA, leave-one-out cross validation, or regularization.


Project # 15 Group members:

Praneeth, Sai

Peng, Xudong

Li, Alice

Vajargah, Shahrzad

Title: Google Analytics Customer Revenue Prediction [1] - A Kaggle Competition

Description: Guess which cabin class in airlines is the most profitable? One might guess economy - but in reality, it's the premium classes that show higher returns. According to research conducted by Wendover productions [2], despite having less than 50 seats and taking up more space than the economy class, premium classes end up driving more revenue than other classes.

In fact, just like airlines, many companies adopt the business model where the vast majority of revenue is derived from a minority group of customers. As a result, data-intensive promotional strategies are getting more and more attention nowadays from marketing teams to further improve company returns.

In this Kaggle competition, we are challenged to analyze a Google Merchanidize Store's customer dataset to predict revenue per customer. We will implement a series of data analytics methods including pre-processing, data augmentation, and parameter tuning. Different classification algorithms will be compared and optimized in order to achieve the best results.

Reference:

[1] Kaggle. (2018, Sep 18). Google Analytics Customer Revenue Prediction. Retrieved from https://www.kaggle.com/c/ga-customer-revenue-prediction

[2] Kottke, J (2017, Mar 17). The economics of airline classes. Retrieved from https://kottke.org/17/03/the-economics-of-airline-classes


Project # 16 Group members:

Wang, Yu Hao

Grant, Aden

McMurray, Andrew

Song, Baizhi

Title: Google Analytics Customer Revenue Prediction - A Kaggle Competition

The 80/20 rule has proven true for many businesses–only a small percentage of customers produce most of the revenue. As such, marketing teams are challenged to make appropriate investments in promotional strategies.

GStore

RStudio, the developer of free and open tools for R and enterprise-ready products for teams to scale and share work, has partnered with Google Cloud and Kaggle to demonstrate the business impact that thorough data analysis can have.

In this competition, you’re challenged to analyze a Google Merchandise Store (also known as GStore, where Google swag is sold) customer dataset to predict revenue per customer. Hopefully, the outcome will be more actionable operational changes and a better use of marketing budgets for those companies who choose to use data analysis on top of GA data.

we will test a variety of classification algorithms to determine an appropriate model.


Project # 17 Group Members:

Jiang, Ya Fan

Zhang, Yuan

Hu, Jerry Jie

Title: Kaggle Competition: Quick, Draw! Doodle Recognition Challenge

Description: Construction of a classifier that can learn from noisy training data and generalize to a clean test set . Training data coming from the Google game "Quick, Draw"


Project # 18 Group Members:

Zhang, Ben

Mall, Sunil

Title: Two Sigma: Using News to Predict Stock Movements

Description: Use news analytics to predict stock price performance. This is subject to change.


Project # 19 Group Members:

Yan Yu Chen

Qisi Deng

Hengxin Li

Bochao Zhang

Our team currently has two interested topics at hand, and we have summarized the objective of each topic below. Please note that we will narrow down our choices after further discussions with the instructor.

Description 1: With 14 percent of American claiming that social media is their most dominant news source, fake news shared on Facebook and Twitter are invading people’s information learning experience. Concomitantly, the quality and nature of online news have been gradually diluted by fake news that are sometimes imperceptible. With an aim of creating an unalloyed Internet surfing experience, we sought to develop a tool that performs fake news detection and classification.

Description 2: Statistics Canada has recently reported an increasing trend of Toronto’s violent crime score. Though the Royal Canadian Mounted Police has put in the effort and endeavor to track crimes, the ambiguous snapshots captured by outdated cameras often hamper the investigation. Motivated by the aforementioned circumstance, our second interest focuses on the accurate numeral and letter identification within variable-resolution images.


Project # 20 Group Members:

Dong, Yongqi (Michael)

Kingston, Stephen

Title: Kaggle--Two Sigma: Using News to Predict Stock Movements

Description: The movement in price of a trade-able security, or stock, on any given day is an aggregation of each individual market participant’s appraisal of the intrinsic value of the underlying company or assets. These values are primarily driven by investors’ expectations of the company’s ability to generate future free cash flow. A steady stream of information on the state of macro and micro-economic variables which affect a company’s operations inform these market actors, primarily through news articles and alerts. We would like to take a universe of news headlines and parse the information into features, which allow us to classify the direction and ‘intensity’ of a stock’s price move, in any given day. Strategies may include various classification methods to determine the most effective solution.


Project # 21 Group members:

Xiao, Alexandre

Zhang, Richard

Ash, Hudson

Zhu, Ziqiu

Title: Image Segmentation with Capsule Networks using CRF loss

Description: Investigate the impact in changing loss function/regularizers on image segmentation tasks with capsule networks.


Project # 22 Group Members:

Lee, Yu Xuan

Heng, Tsen Yee

Title: Two Sigma: Using News to Predict Stock Movements

Description: Use news analytics to predict stock price performance. This is subject to change.



Project # 23 Group Members:

Bayati, Mahdiyeh

Malek Mohammadi, Saber

Luong, Vincent


Title: Human Protein Atlas Image Classification


Description: The Human Protein Atlas is a Sweden-based initiative aimed at mapping all human proteins in cells, tissues and organs.


Project # 24 Group Members:

Wu Yutong,

Wang Shuyue,

Jiao Yan

Title: Kaggle Competition: Quora Insincere Questions Classification

Description: