Discover and read the best of Twitter Threads about #deeplearning
Most recents (6)
#Tweetorial on #Diagnostics and #Screening interpretation.
An otherwise healthy 40 year old woman comes to you after reading on the internet about a terrible disease that one in a thousand women get, and a highly accurate test that can save her life.
An otherwise healthy 40 year old woman comes to you after reading on the internet about a terrible disease that one in a thousand women get, and a highly accurate test that can save her life.
The test is over 99% accurate in people with the disease. For those without disease, the test is only wrong 5% of the time.
You order this test and it comes back positive. The woman anxiously asks you, do I have the disease? What is the chance this woman has the disease?
You order this test and it comes back positive. The woman anxiously asks you, do I have the disease? What is the chance this woman has the disease?
Assuming they weren't immediately fooled by the "test is only wrong 5 % of the time," most I've asked correctly recognize the stats provided are Sensitivity = 99% and Specificity = 95%, and that the objective is to determine the Positive Predictive Value.
@DeepIndaba top tips from an extremely useful panel discussion on how to write a great research paper:
- tell one story throughout the paper. make sure this story is clear and that you are able to frame your paper in 1 sentence.
- tell one story throughout the paper. make sure this story is clear and that you are able to frame your paper in 1 sentence.
- be clear about what the problem is and about the solution you are putting forward.
- you don't have to put everything you did in everything you write.
- be academically honest. don't oversell your results.
- you don't have to put everything you did in everything you write.
- be academically honest. don't oversell your results.
- introduce a concept and its mathematical notation at the same time to keep your reader in the loop.
- spend time on creating images that help to visualize concepts, put them at the top of the page with a self-contained caption.
- spend time on creating images that help to visualize concepts, put them at the top of the page with a self-contained caption.
1/ What are #deepfakes + #AI generated synthetic media; what threats do they pose to #humanrights, #journalism and #publicsphere? What should we fear? What can we do? Thread w/ key tech + usages from recent expert mtg summarizing blog.witness.org/2018/07/deepfa…
2/We've had fake images and CGI for years, so what's different now (beyond enabling us to transplant Nicolas Cage's face to other people). The ease of making #deepfakes is captured by the vlogger Tom Scott 
3/ = Barriers to entry to manipulate audio and video are falling - costs less, needs less tech expertise, uses open-source code + cloud computing power. Plus, sophistication of manipulation of social media spaces by bad actors makes it easier to weaponize and to micro-target.
Afternoon twitterverse! Let’s talk about AI in Radiology, which is the main focus in my research.
Any talk of AI begs for a definition of AI, and there are as many definitions as there startups that are “AI-enabled”.
Any talk of AI begs for a definition of AI, and there are as many definitions as there startups that are “AI-enabled”.
For our purposes we'll just call anything that performs one of the higher level behaviours associated with animals e.g. learning, planning, problem-solving, creating etc.
Inspired by the big ol' long list of deep learning models I saw this morning, and @SpaceWhaleRider's love of science-y A-Z lists, I've decided to create an A to Z series of tweets on popular #MachineLearning and #DeepLearning methods / algorithms.
Ready? Here we go:
Ready? Here we go:
A is for... the Apriori Algorithm!
Intended to mine frequent itemsets for Boolean association rules (like market basket analysis). Ex: if someone purchases the same products as you, in general, then you'd probably purchase something they've purchased.
cran.r-project.org/web/packages/a…
Intended to mine frequent itemsets for Boolean association rules (like market basket analysis). Ex: if someone purchases the same products as you, in general, then you'd probably purchase something they've purchased.
cran.r-project.org/web/packages/a…
B is for... Bootstrapped Aggregation (Bagging)!
This is an ensemble meta-algorithm designed to improve the stability and accuracy of machine learning algorithms used in statistical classification+regression. Reduces variance, helps to avoid overfitting.
Example: Random Forests.
This is an ensemble meta-algorithm designed to improve the stability and accuracy of machine learning algorithms used in statistical classification+regression. Reduces variance, helps to avoid overfitting.
Example: Random Forests.
#DeepNeuralNet #LearningToSee (havin a hard time cos I'm playin w LR momentum gradclip etc in realtime - no post vfx, all from the DNN)
