Very good article about using Alternating Least Squares (ALS) model for Collaborative filtering based on implicit data.
https://medium.com/radon-dev/als-implicit-collaborative-filtering-5ed653ba39fe
https://medium.com/radon-dev/als-implicit-collaborative-filtering-5ed653ba39fe
Medium
ALS Implicit Collaborative Filtering
Continuing on the collaborative filtering theme from my collaborative filtering with binary data example i’m going to look at another way…
Some cheatsheet with pros/cons for popular ML algorithms
https://recast.ai/blog/machine-learning-algorithms/2/
https://recast.ai/blog/machine-learning-algorithms/2/
Good article if you are looking how to make your model smaller https://arxiv.org/abs/1801.06434v5
All about convolutions and their types
https://towardsdatascience.com/types-of-convolutions-in-deep-learning-717013397f4d
https://towardsdatascience.com/types-of-convolutions-in-deep-learning-717013397f4d
Medium
An Introduction to different Types of Convolutions in Deep Learning
Let me give you a quick overview of different types of convolutions and what their benefits are. For the sake of simplicity, I’m focussing…
Adversarial attacks comes to the audio networks.
https://nicholas.carlini.com/code/audio_adversarial_examples/
https://nicholas.carlini.com/code/audio_adversarial_examples/
Pinterest Lens. It's an old but usefull paper for those who are building recommendation engines.
https://arxiv.org/abs/1505.07647
https://arxiv.org/abs/1505.07647
Interesting story about RL to read
http://amid.fish/reproducing-deep-rl
http://amid.fish/reproducing-deep-rl
Interesting NLP model architecture
http://nlp.seas.harvard.edu/2018/04/03/attention.html
http://nlp.seas.harvard.edu/2018/04/03/attention.html
New plasticity networks from UBER
https://eng.uber.com/differentiable-plasticity/
https://eng.uber.com/differentiable-plasticity/
Uber Engineering Blog
Differentiable Plasticity: A New Method for Learning to Learn
Differentiable Plasticity is a new machine learning method for training neural networks to change their connection weights adaptively even after training is completed, allowing a form of learning inspired by the lifelong plasticity of biological brains.
Very interesting article about grid-cells in AI
https://deepmind.com/blog/grid-cells/
https://deepmind.com/blog/grid-cells/
Deepmind
Navigating with grid-like representations in artificial agents
Most animals, including humans, are able to flexibly navigate the world they live in – exploring new areas, returning quickly to remembered places, and taking shortcuts. Indeed, these abilities feel so easy and natural that it is not immediately obvious how…
Interesting set of cool NLP papers from Alexandr
https://www.facebook.com/rachnogstyle/posts/1956621254372079
https://www.facebook.com/rachnogstyle/posts/1956621254372079
Facebook
Alexandr Honchar
How we roll #2 В последнее время мне часто стали попадаться интересные пейперы по NLP, вот несколько из них: Learning Semantic Textual Similarity from Conversations, Google...
Things need to know about Collaborative Filtering in Recommender systems. Why straightforward CF almost always will give bad result.
https://www.researchgate.net/publication/260367537_Improving_Collaborative_Filtering_based_Recommenders_using_Topic_Modelling?_sg=8hKxvTvUaMbLsIfTkffdC8ueLalHxiNnZhS6vwOCWvsnN76KuLU4jNq_YFe4h1Qbe4sNx8kyPA
https://www.researchgate.net/publication/260367537_Improving_Collaborative_Filtering_based_Recommenders_using_Topic_Modelling?_sg=8hKxvTvUaMbLsIfTkffdC8ueLalHxiNnZhS6vwOCWvsnN76KuLU4jNq_YFe4h1Qbe4sNx8kyPA
Very useful library for visualisation of LDA topic modeling results
https://github.com/bmabey/pyLDAvis
https://github.com/bmabey/pyLDAvis
GitHub
GitHub - bmabey/pyLDAvis: Python library for interactive topic model visualization. Port of the R LDAvis package.
Python library for interactive topic model visualization. Port of the R LDAvis package. - bmabey/pyLDAvis
Interesint Stanford competition on X-Ray abnormalities detection, and what more interesting is a free dataset)
https://stanfordmlgroup.github.io/competitions/mura/
https://stanfordmlgroup.github.io/competitions/mura/
stanfordmlgroup.github.io
MURA Dataset: Towards Radiologist-Level Abnormality Detection in Musculoskeletal Radiographs
MURA is a large dataset of bone X-rays. Algorithms are tasked with determining whether an X-ray study is normal or abnormal.
Hey guys, we have good job vacancy in the area of Text-to-Speech generation.
Required skills:
- At least 4 year of experience with DS
- Experience in speech generation
- Experience in Python/Scala (at least 5 years of experience)
- English (upper intermediate)
For additional information please write to
Margarita Vitiuk (https://www.facebook.com/margoffline)
Required skills:
- At least 4 year of experience with DS
- Experience in speech generation
- Experience in Python/Scala (at least 5 years of experience)
- English (upper intermediate)
For additional information please write to
Margarita Vitiuk (https://www.facebook.com/margoffline)