Trivadis Navigator
Trivadis BlogStart
Leistungsangebot
Kompetenzen
Training
News & PR
Events
Über Trivadis
Login
Join
Sign in
Options
RSS for posts
OK
Tags
benchmarks
Client Programming
Data Science
Deep Learning
forecasting
Java
jdbc
Machine Learning
Natural Language Processing
neural networks
Optimizer
Oracle
Performance
Profiling
Python
R
recurrent neural network
sentiment analysis
Statistics
Swingbench
tensorflow
timeseries
Tracing
word vectors
word2vec
Home
»
Sigrid Keydana
Sigrid Keydana
RSS for posts
Subscribe via RSS
Sort by:
Most Recent

Most Views

Most Comments
Excerpt View

Full Post View
Sigrid Keydana
Update
Posted
2 months ago
by
Sigrid Keydana
I’m an applied researcher at RStudio, where I contribute to the rtensorflow family of packages (e.g., tfprobability). I write about doing deep learning from R on the TensorFlow for R blog. If you’re interested in DL/ML/probability and R,...
Sigrid Keydana
Deep learning, concepts and frameworks: Find your way through the jungle (talk)
Posted
over 1 year ago
by
Sigrid Keydana
Today at OOP in Munich, I had an indepth talk on deep learning, including applications, basic concepts as well as practical demos with Tensorflow, Keras and PyTorch. As usual, the slides are on RPubs, split up into 2 parts because of the plenty of images...
Sigrid Keydana
Practical Deep Learning (talk)
Posted
over 1 year ago
by
Sigrid Keydana
Yesterday at IT Tage 2017, I had an introductorylevel talk on deep learning. After giving an overview of concepts and frameworks, I zoomed in on the task of image classification using Keras, Tensorflow and PyTorch, not aiming for high classification...
Sigrid Keydana
I’m a developer, why should I care about matrices or calculus? (talk at MLConference 2017)
Posted
over 1 year ago
by
Sigrid Keydana
Yesterday at ML Conference, which took place this year for the first time, I had a talk on cool bits of calculus and linear algebra that are useful and fun to know if you’re writing code for deep learning and/or machine learning. Originally, the...
Sigrid Keydana
Plus/minus what? Let’s talk about uncertainty (talk)
Posted
over 1 year ago
by
Sigrid Keydana
Last week at DOAG 2017, I had two talks, one about deep learning with DL4J (slides here) and one about how to communicate uncertainty (or rather: how to construct prediction intervals for various methods / in various frameworks ranging from simple linear...
Sigrid Keydana
Dynamic forecasts – with Bayesian linear models and neural networks (talk at Predictive Analytics World Berlin)
Posted
over 1 year ago
by
Sigrid Keydana
I really wish I had the time to write an article about the conference, instead of just posting the slides! Predictive Analytics World was super inspiring, not just in a technical way but also as to the broader picture of today’s data science / AI...
Sigrid Keydana
Deep Learning with Keras – using R (talk)
Posted
over 1 year ago
by
Sigrid Keydana
This week in Kassel, [R]Kenntnistage 2017 took place, organised by EODA. It was all about Data Science (with R, mostly, as you could guess): Speakers presented interesting applications in industry, manufacturing, ecology, journalism and other fields,...
Sigrid Keydana
Time series shootout: ARIMA vs. LSTM (talk)
Posted
over 1 year ago
by
Sigrid Keydana
Yesterday, the Munich datageeks Data Day took place. It was a totally fun event – great to see how much is going on, datasciencewise, in and around Munich, and how many people are interested in the topic! (By the way, I think that more than half...
Sigrid Keydana
Automatic Crack Detection – with Deep Learning
Posted
over 1 year ago
by
Sigrid Keydana
On Friday at DOAG Big Data Days, I presented one possible application of deep learning: using deep learning for automatic crack detection – with some background theory, a Keras model trained from scratch, and the use of VGG16 pretrained on Imagenet...
Sigrid Keydana
Deep Learning, deeplearning4j and Outlier Detection: Talks at Trivadis Tech Event
Posted
over 1 year ago
by
Sigrid Keydana
Last weekend, another edition of Trivadis Tech Event took place. As usual, it was great fun and a great source of inspiration. I had the occasion to talk about deep learning twice: One talk was an intro to DL4J (deeplearning4j), zooming in on a few aspects...
Sigrid Keydana
Haskell, R, and HaskellR: Combining the best of two worlds (talk at UseR! 2017)
Posted
over 1 year ago
by
Sigrid Keydana
Earlier today, I presented at UseR! 2017 about HaskellR: a great piece of software, developed by Tweag I/O, that allows to seemlessly use R from Haskell. It was my first UseR!, it was a great experience, and if I had the time I’d like to write a...
Sigrid Keydana
Time series prediction – with deep learning
Posted
over 2 years ago
by
Sigrid Keydana
More and more often, and in more and more different areas, deep learning is making its appearance in the world around us. Many small and medium businesses, however, will probably still think – Deep Learning, that’s for Google, Facebook &...
Sigrid Keydana
Deep Learning in Action (the less mathy version, this time)
Posted
over 2 years ago
by
Sigrid Keydana
On Tuesday at Hochschule München, Fakultät für Informatik and Mathematik I again gave a guest lecture on Deep Learning (RPubs, github, pdf). This time, it was more about applications than about matrices, more about general understanding than about architecture...
Sigrid Keydana
R 4 hackers
Posted
over 2 years ago
by
Sigrid Keydana
Yesterday at Trivadis Tech Event, I talked about R for Hackers. It was the first session slot on Sunday morning, it was a crazy, nerdy topic, and yet there were, like, 30 people attending! An emphatic thank you to everyone who came! R a crazy, nerdy topic...
Sigrid Keydana
Deep Learning in Action
Posted
over 2 years ago
by
Sigrid Keydana
On Wednesday at Hochschule München, Fakultät für Informatik and Mathematik I presented about Deep Learning (nbviewer, github, pdf). Mainly concepts (what’s “deep” in Deep Learning, backpropagation, how to optimize …) and architectures...
Sigrid Keydana
R for SQListas (3): Classifying Digits with TensorFlow
Posted
over 2 years ago
by
Sigrid Keydana
Yesterday at PASS Meetup Munich, I talked about R for SQListas – thanks again for your interest and attention guys, it was a very nice evening! Actually, in addition to the content from that original presentation, which I’ve also covered in...
Sigrid Keydana
R for SQListas (2): Forecasting the Future
Posted
over 2 years ago
by
Sigrid Keydana
R for SQListas, part 2 Welcome to part 2 of my “R for SQListas” series. Last time, it was all about how to get started with R if you’re a SQL girl (or guy) and that basically meant an introduction to Hadley Wickham’s dplyr and...
Sigrid Keydana
Analyse de sentiments de critiques cinématographiques – version française
Posted
over 2 years ago
by
Sigrid Keydana
This is just an ultra short post saying that last Tuesday, I had the honor of presenting my “Sentiment Analysis of Movie Reviews” talk at Swiss Data Forum – in French Thanks again guys for having me, and for your patience So here’s...
Sigrid Keydana
R for SQListas (1): Welcome to the Tidyverse
Posted
over 2 years ago
by
Sigrid Keydana
R for SQListas, what’s that about? This is the 2part blog version of a talk I’ve given at DOAG Conference this week. I’ve also uploaded the slides (no ppt; just pretty R presentation ) to the articles section, but if you’d like...
Sigrid Keydana
Sentiment Analysis of Movie Reviews (3): doc2vec
Posted
over 2 years ago
by
Sigrid Keydana
This is the last – for now – installment of my miniseries on sentiment analysis of the Stanford collection of IMDB reviews. So far, we’ve had a look at classical bagofwords models and word vectors (word2vec). We saw that from the...
Sigrid Keydana
Sentiment Analysis of Movie Reviews (2): word2vec
Posted
over 2 years ago
by
Sigrid Keydana
This is the continuation of my miniseries on sentiment analysis of movie reviews. Last time, we had a look at how well classical bagofwords models worked for classification of the Stanford collection of IMDB reviews. As it turned out, the “winner”...
Sigrid Keydana
Sentiment Analysis of Movie Reviews (1): Word Count Models
Posted
over 2 years ago
by
Sigrid Keydana
Imagine I show you a book review, on amazon.com, say. Imagine I hide the number of stars, – all you get to see is the number of stars. And now I’m asking you, that review, is it good or bad? Just two categories, good or bad. That’s easy...
Sigrid Keydana
Sentiment Analysis of Movie Reviews (talk)
Posted
over 2 years ago
by
Sigrid Keydana
Yesterday at Tech Event, which was great as always, I presented on sentiment analysis, taking as example movie reviews. I intend to write a little series of blog posts on this, but as I’m not sure when exactly I’ll get to this, here are the...
Sigrid Keydana
Doing Data Science
Posted
over 2 years ago
by
Sigrid Keydana
This is another untechnical post – actually, it’s even a personal one. If you’ve been to this blog lately, you may have noticed something, that is, the absence of something – the absence of posts over nearly six months …...
Sigrid Keydana
IT Myths (1): Best Practices
Posted
over 3 years ago
by
Sigrid Keydana
IT Myths (1): Best Practices I don’t know about you, but I feel uncomfortable when asked about “Best Practices”. I manage to give the expected answers, but I still feel uncomfortable. Now, if you’re one of the people who liked...
Page 1 of 2 (43 items)
1
2