Search for tag: "dataset"

Skills in Heritage Data Science: Meet the Dogs of 19th Century Denmark

Henriette Roued-Cunliffe (University of Copenhagen) discusses how to create a smooth learning curve for data-led research in the humanities.In the humanities and the heritage sector, Henriette has…

From  Roisin O'Brien on January 20th, 2021 0 likes 6 plays 0  

FDS-S2-02-2-5 Maximum likelihood estimation of logistic regression coefficients

We introduce the principle of maximum likelihood, and show how to derive the likelihood as a function of the coefficients for logistic regression. We also mention one topical application of logistic…

From  David Sterratt on January 20th, 2021 0 likes 125 plays 0  

FDS-S2-02-2-3 Multiple logistic regression and confidence and intervals

We extend logistic regression to multiple independent variables, and show how we can use the boostrap to estimate confidence intervals for coefficients, and to test hypotheses.

From  David Sterratt on January 20th, 2021 0 likes 147 plays 0  

FDS-S2-02-4 Issues in hypothesis testing

We consider 3 issues in hypothesis testing: Type I and Type II errors; cherry-picking, p-value hacking etc., and a short discussion about the possibility that hypothesis-driven research can hinder…

From  David Sterratt on January 18th, 2021 0 likes 125 plays 0  

Can we Trust Data-Driven Scientific Discoveries?

Genevera Allen discusses "Machine Learning & Scientific Reproducibility: Can we Trust Data-Driven Scientific Discoveries?" As more and more scientific domains are collecting vast…

From  Belle Taylor on December 18th, 2020 0 likes 9 plays 0  

MLP Interviews - Leonie Bossemeyer

Machine Learning Practical interviews - Winter 2020 - Session 2/4. Leonie Bossmeyer is an MSc graduate in Data Science at the University of Edinburgh, and is currently an MSc student in Quantitative…

From  Pavlos Andreadis on December 7th, 2020 1 likes 35 plays 0  

IDS - Week 10 - 03 - AE - The Office, Part 1

Predicting IMDB ratings of The Office episodes. Part 1 of 2: Data preparation and feature engineering.

From  Mine Cetinkaya-Rundel on November 23rd, 2020 0 likes 9 plays 0  

IDS - Week 09 - 03 - Prediction and overfitting

Making predictions based on models and splitting data into training and testing sets to avoid overfitting

From  Mine Cetinkaya-Rundel on November 16th, 2020 0 likes 28 plays 0  

ML4: An introduction to Classification

Here, we explain what is meant by a (binary) classifier. It is a black box that takes in some data and predicts whether it belongs to one of two possible classes. We also describe how we can split…

From  Elliot Crowley on November 5th, 2020 0 likes 8 plays 0  

ML3: Dimensionality Reduction using Principal Component Analysis

In this video, we will learn that we can use Principal Component Analysis (PCA) to find a transformation matrix that minimises reconstruction error for dimensionality reduction. We also show how this…

From  Elliot Crowley on November 5th, 2020 0 likes 16 plays 0  

ML2: Dimensionality Reduction

In this second video, we motivate why it is useful to reduce the dimensionality of your data, and describe how this can be done linearly, using a transformation matrix. We describe a setup whereby we…

From  Elliot Crowley on November 5th, 2020 0 likes 13 plays 0  

Professional Skills for GAFS (1) - Week 7 - Answers to Mondays Questions

In this video, Jill shows the ggplot answers to the questions we left undone in Monday's farm accounts data. Please note, captions are autogenerated

From  Jill MacKay on November 4th, 2020 0 likes 3 plays 0  

Using existing, open, data for your dissertation research (CSE & CMVM)

Want to find some research data you can analyse for your dissertation? Working to a tight deadline? The Research Data Service can help you find openly-licensed research datasets to choose from, which…

From  Pauline Ward on November 4th, 2020 0 likes 20 plays 0  

ML1: Representing your data

In the first video, we learn how we can represent data from a multitude of sources as vectors. We show that these vectors can be stacked into a matrix to represent an entire dataset, and the…

From  Elliot Crowley on November 3rd, 2020 0 likes 26 plays 0  

USMR lecture 7 part 2

independence; influence; model criticism

From  Martin Corley on November 1st, 2020 0 likes 194 plays 0  

USMR lecture 7 part 1

model criticism

From  Martin Corley on November 1st, 2020 0 likes 207 plays 0