Medijski sadržaj
- Tweetovi
- Tweetovi i odgovori
- Medijski sadržaj, trenutna stranica.
-
IMO, this is the best work I've ever read on AI & Human Values Highly recommended read for everyone in the
#AI field It's a dense read - but push through. You'll be glad you did.#100DaysOfMLCode#ArtificialIntelligence#DeepLearning#AIForGood https://twitter.com/IasonGabriel/status/1222154213674967040 …pic.twitter.com/HXqgotAZOX
-
When I learn new idea, I must repeatedly learn it from multiple
#tutorials before it *clicks* If you're learning#convolutional nets - add this to your list It discusses#CNNs for: - images - audio - databases#100DaysOfMLCode#100DaysOfCode#AI http://brohrer.github.io/how_convolutional_neural_networks_work.html …pic.twitter.com/LKURUK36QQ
-
#TransferLearning is one of the most important#AI techniques I don't often recommend PhD Thesis' -@seb_ruder's is exceptional. He's a brilliant writer! Check out this taxonomy / table of contents!!!

#100DaysOfMLCode#100DaysOfCode https://ruder.io/thesis/neural_transfer_learning_for_nlp.pdf …pic.twitter.com/ZSbZSwD9DT
-
After a year of dev, I am *extremely* excited to share this step-by-step
#notebook tutorial Goal: to be the *easiest* intro to#privacy preserving,#decentralized Deep Learning It's in@PyTorch I hope you enjoy it#GDPR#100DaysOfMLCode#100DaysOfCode https://github.com/OpenMined/PySyft/tree/master/examples/tutorials …pic.twitter.com/8XypqZ1TDS
-
If you've wondered - "Which
#DeepLearning optimizer should I use?#SGD?#Adagrad?#RMSProp?" This blogpost by@seb_ruder is the best explanation I've seen. It's a surprisingly easy read! http://ruder.io/optimizing-gradient-descent/ … Definitely a great#100DaysOfMLCode /#100DaysOfCode project!pic.twitter.com/P4VWcL55eQ -
The *easiest* way to learn Deep Learning is to build it from scratch! IMO, the same is true when learning a Deep Learning framework. In
#GrokkingDeepLearning I show how to build a@PyTorch-like framework Here's the step-by-step code!!#100DaysOfMLCode https://github.com/iamtrask/Grokking-Deep-Learning …pic.twitter.com/xvekVP04qP
-
King - Man + Woman = Queen How does this work?
@seb_ruder does an excellent job laying out the foundations. The code at the end is also a great#100DaysOfMLCode project. Article: http://ruder.io/word-embeddings-1/index.html …#100DaysOfCode#NLP#DataScience#AI#MachineLearningpic.twitter.com/MverDPlBe0
-
For all you *aspiring*
@PyTorch users! @KaiLashArul has written a *very* nice fast-track intro!#100DaysOfMLCode#100DaysOfCode https://github.com/Kaixhin/grokking-pytorch …pic.twitter.com/bx7NHjdK3L
-
Want to know the future of insurance? It’s personal data modifying your coverage costs
@Allstate now offers variable pricing based on a driving tracker in your car Wouldn’t be surprised if medical insurance has this for exercise/lifestyle soon https://clubthrifty.com/allstate-drivewise-sham/ …pic.twitter.com/gxt6NiMu5M
Prikaži ovu nit -
Attention is one of the most important breakthroughs in the history of Deep Learning. This
@distillpub is definitively the best explanation of it I've seen. For#100DaysOfMLCode /#100DaysOfCode folks - try building an attention mechanism from scratch! https://distill.pub/2016/augmented-rnns/ …pic.twitter.com/vzXBcQmjfG
-
This is the *most* extensive list of "From Scratch Machine Learning" I've ever seen. It's a *golden* resource if you learn like I do (by building things from scratch). Happy learning!
#100DaysOfMLCode#100DaysOfCode https://github.com/eriklindernoren/ML-From-Scratch …pic.twitter.com/e1mIbPb4nn
-
This series of
#Jupyter#Notebooks is a VERY nice step-by-step intro to data science and machine learning. If you're just starting out - I recommend walking through these notebooks as a first primer Definitely a great#100DaysOfMLCode project https://github.com/rasbt/python-machine-learning-book-2nd-edition …pic.twitter.com/xwjzkfnH4u
-
Machine Learning in a company is 10% Data Science & 90% other challenges It's VERY hard. Everything in this guide is ON POINT, and it's stuff you won't learn in an ML book "Best Practices of ML Engineering" This is a lifesaver
#100DaysOfMLCode project http://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf …pic.twitter.com/eYJ5KpQmVt
-
"A Beginner's Guide to the Mathematics of Neural Networks" ... a nice gem
And *very* cool illustrations !!!
#100DaysOfMLCode http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.161.3556&rep=rep1&type=pdf …pic.twitter.com/cAAI8ykMyU
-
This year I wrote a book teaching Deep Learning - it's goal is to be the easiest intro possible In the book, each lesson builds a neural component *from scratch* in
#NumPy Each *from scratch* toy code example is in the Github below.#100daysofMLcode https://github.com/iamtrask/Grokking-Deep-Learning …pic.twitter.com/upyCPWD7zt
-
For anyone who has ever thought - "Can I learn the math needed for Deep Learning all in one place (& maybe skip the other stuff)?" - this is quite a nice resource! "The Matrix Calculus You Need For Deep Learning" http://explained.ai/matrix-calculus/index.html …
#100DaysOfMLCode (Table of Contents
)pic.twitter.com/RJTJgxwXw4
-
#AI is only relevant for problems we have data for The *most* important problems are problems about people#cancer#loneliness,#depression,#conflict, etc. Want to solve them? Solve#privacy In my talk, I explain why: https://www.facebook.com/pytorch/videos/783738105413646/?t=7922 …#100DaysOfMLCode#100DaysOfCodepic.twitter.com/1YyHmlNx4C
-
Same time next week :) https://www.youtube.com/watch?v=_6ascseknKc&feature=youtu.be …
-
How should you learn an algorithm? 1) Find an implementation 2) Strip it down to the absolute bare bones 3) Teach it line-by-line in a blog Here's mine - "A Neural Network in 11 LInes of Python" I already knew NNs - still worth it !!!
#100DaysOfMLCode https://iamtrask.github.io/2015/07/12/basic-python-network/ …pic.twitter.com/sOOvFmQH3E
-
Probably the best GANs tutorial I've seen - written by
@devnag The best tutorials strip away all the complexity into the simplest example possible. That's what I like about this#tutorial... "50 lines of PyTorch"#100DaysOfMLCode#100DaysOfCode https://medium.com/@devnag/generative-adversarial-networks-gans-in-50-lines-of-code-pytorch-e81b79659e3f …pic.twitter.com/7mKDJeknpa
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.