Subscribe to DSC Newsletter
Frank Raulf
  • Male
  • Frankfurt
  • Germany
Share on Facebook
Share

Gifts Received

Gift

Frank Raulf has not received any gifts yet

Give a Gift

 

Frank Raulf's Page

Latest Activity

Umar Shehu liked Frank Raulf's blog post Data Quality Maintenance
Nov 15, 2020
Vidya Manu Shankar liked Frank Raulf's blog post Introduction to Gradient Decent
Jun 29, 2020
Frank Raulf posted a blog post

Introduction to Gradient Decent

The gradient decent approach is used in many algorithms to minimize loss functions. In this introduction we will see how exactly a gradient descent works. In addition, some special features will be pointed out. We will be guided by a practical example.First of all we need a loss function. A very common approach iswhere y are the true observations of the target variable…See More
Jun 28, 2020
Frank Raulf's blog post was featured

Introduction to Gradient Decent

The gradient decent approach is used in many algorithms to minimize loss functions. In this introduction we will see how exactly a gradient descent works. In addition, some special features will be pointed out. We will be guided by a practical example.First of all we need a loss function. A very common approach iswhere y are the true observations of the target variable…See More
Jun 25, 2020
Frank Raulf liked Vincent Granville's blog post My data science journey
Jun 23, 2020
Frank Raulf updated their profile
Apr 27, 2020
Frank Raulf liked Shreya Gupta's blog post Importing Data in R
Feb 7, 2020
Frank Raulf's blog post was featured

How to make time-data cyclical for prediction?

There are many ways to deal with time-data. Sometimes one can use it as time-series to take possible trends into account. Sometimes this is not possible because time can not be arranged in a sequence. For example, if there are just weekdays (1 to 7) in a dataset over several month. In this case one could use one-hot-encoding. However, considering minutes or seconds of a day one-hot-encoding might lead to high complexity. Another approach is to make time cyclical. This approach leads to a lower…See More
Jan 26, 2020
Deborah Hurley commented on Frank Raulf's blog post Which one is faster in multiprocessing, R or Python?
"Great information and thank you for doing this work!"
Jan 23, 2020
Deborah Hurley commented on Frank Raulf's blog post Loop-Runtime Comparison R, RCPP, Python
"Excellent information and thank you for doing this work!  As always, the information posted from DSC is excellent and useful avoiding the hype which can be distracting."
Jan 23, 2020
Deborah Hurley liked Frank Raulf's blog post Loop-Runtime Comparison R, RCPP, Python
Jan 23, 2020
Frank Raulf liked Capri Granville's blog post What are the Typical Data Scientist Profiles on LinkedIn? Survey Results
Jan 8, 2020
Frank Raulf liked Vincent Granville's blog post Weekly Digest, January 6
Jan 6, 2020
Frank Raulf posted blog posts
Jan 6, 2020
Frank Raulf's 2 blog posts were featured
Jan 5, 2020
Frank Raulf liked Vincent Granville's blog post Invitation to Join Data Science Central
Jan 4, 2020

Profile Information

Job Title:
Senior Data Scientist
Seniority:
Technical
Job Function:
Data Science, Machine Learning, AI, Business Analytics, Deep Learning
Industry:
IT
Short Bio:
Favourite languages: R, Python.
Favourite topics: Simulation, regression methods, API, web-scraping.
Interested in: MLP, CNN, RNN
LinkedIn Profile:
http://https://www.kaggle.com/frankmollard
Interests:
Contributing, Networking, New venture

Frank Raulf's Blog

Introduction to Gradient Decent

Posted on June 24, 2020 at 7:00am 0 Comments

The gradient decent approach is used in many algorithms to minimize loss functions. In this introduction we will see how exactly a gradient descent works. In addition, some special features will be pointed out. We will be guided by a practical example.…

Continue

How to make time-data cyclical for prediction?

Posted on January 26, 2020 at 4:00am 0 Comments

There are many ways to deal with time-data. Sometimes one can use it as time-series to take possible trends into account. Sometimes this is not possible because time can not be arranged in a sequence. For example, if there are just weekdays (1 to 7) in a dataset over several month. In this case one could use one-hot-encoding. However, considering minutes or seconds of a day one-hot-encoding might lead to high complexity. Another approach is to make time cyclical. This approach leads to a…

Continue

Setting the Cutoff Criterion for Probabilistic Models

Posted on January 4, 2020 at 3:00am 0 Comments

For decision making, human perception tends to arrange probabilities into above 50% and below - which is plausible. For most probabilistic models in contrast, this is not the case at all. Frequently, resulting probabilities are neither normal distributed between zero and one with a mean of 0.5 nor correct in terms of absolute values. This is not seldom an issue accompanied with the existence of a minority class - in the underlying dataset.

For example, if the result of a…

Continue

Naive Bayes Classifier using Kernel Density Estimation (with example)

Posted on January 3, 2020 at 4:30am 0 Comments

Bayesian inference is the re-allocation of credibilities over possibilities [Krutschke 2015]. This means that a bayesian statistician has an “a priori” opinion regarding the probabilities of an event:

p(d)   (1)

By observing new data x, the statistician will adjust his opinions to get the "a posteriori" probabilities.

p(d|x)   (2)

The conditional probability of an event d given x is the share of  the joint…

Continue

Comment Wall

You need to be a member of Data Science Central to add comments!

Join Data Science Central

  • No comments yet!
 
 
 

© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service