Interactive Language Learning by Question Answering. https://arxiv.org/abs/1908.10909

[🛠Understand basics of Deep Learning from scratch🛠]

If you're willing to understand how neural networks work behind the scene and debug the back-propagation algorithm step by step by yourself, these slides should be a good starting point.

We will cover deep learning popular applications, the concept of the artificial neuron and how it relates to the biological one, the perceptron and the multi-layer one. We'll also dive in activation functions, loss functions and formalize the training of a neural net via the back-propagation algorithm.

In the last part, you'll learn how to code a fully functioning trainable neural network from scratch. In pure python code only, with no frameworks involved.

slides: https://ahmedbesbes.com/introduction-to-neural-networks-and-deep-learning-from-scratch.html
code: https://github.com/ahmedbesbes/Neural-Network-from-scratch

#deeplearning

Machine Learning From Scratch

Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

GitHub, by Erik Linder-Noren : https://github.com/eriklindernoren/ML-From-Scratch

#machinelearning #deeplearning #deepreinforcementlearning

A Probabilistic Representation of Deep Learning

Xinjie Lan, Kenneth E. Barner : https://arxiv.org/abs/1908.09772v1

#deeplearning #machinelearning #neuralnetwork

Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT

Blog by Victor Sanh : https://medium.com/huggingface/distilbert-8cf3380435b5

#MachineLearning #NLP #Bert #Distillation #Transformers

Hierarchical Text Classification with Reinforced Label Assignment

Mao et al.: https://arxiv.org/abs/1908.10419

#InformationRetrieval #MachineLearning #ReinforcementLearning

Learning to Discover Novel Visual Categories via Deep Transfer Clustering

Han et al.: https://arxiv.org/abs/1908.09884

#ArtificialIntelligence #DeepLearning #NeuralNetworks

Finally, AI-Based Painting is here! - https://youtu.be/IqHs_DkmDVo

Actuarial Reserve Risk Classification with Gaussian Mixture
GitHub, by Abdelrahman Elsemary : https://github.com/Elsemary/Actuarial-Reserve-Risk-Classification-with-Gaussian-Mixture
#actuarialscience #machinelearning #mathematics

The top 20 free online CS courses of all time, via Class Central

Full list: bit.ly/CC100MOOCs #learntocode #MondayMotivation

How to Deploy a Machine Learning Model
https://towardsdatascience.com/how-to-deploy-a-machine-learning-model-dc51200fe8cf

Probability Learning III: Maximum Likelihood
https://towardsdatascience.com/probability-learning-iii-maximum-likelihood-e78d5ebea80c

Learning to Learn with Probabilistic Task Embeddings
https://bair.berkeley.edu/blog/2019/06/10/pearl/

Open Datasets for Machine Learning https://lionbridge.ai/business-resources/open-datasets-for-machine-learning/

Scientists Find Evidence The Human Brain Can Create Structures in Up to 11 Dimensions
https://www.sciencealert.com/scientists-find-evidence-the-human-brain-can-create-structures-in-up-to-11-dimensions

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting. https://arxiv.org/abs/1908.10937

Saccader: Improving Accuracy of Hard Attention Models for Vision
Gamaleldin F. Elsayed, Simon Kornblith, Quoc V. Le : https://arxiv.org/abs/1908.07644
#ArtificialIntelligence #DeepLearning #MachineLearning

ACL 2019 Thoughts and Notes
By Vinit Ravishankar, Daniel Hershcovich; edited by Artur Kulmizev, Mostafa Abdou : https://supernlp.github.io/2019/08/16/acl-2019/
#naturallanguageprocessing #machinelearning #deeplearning

wish I could add Bengio too.
[sota= state-of-the-art]

Most common libraries for Natural Language Processing:

CoreNLP from Stanford group:
https://stanfordnlp.github.io/CoreNLP/index.html

NLTK, the most widely-mentioned NLP library for Python:
https://www.nltk.org/

TextBlob, a user-friendly and intuitive NLTK interface:
https://textblob.readthedocs.io/en/dev/index.html

Gensim, a library for document similarity analysis:
https://radimrehurek.com/gensim/

SpaCy, an industrial-strength NLP library built for performance:
https://spacy.io/docs/

Source: https://itsvit.com/blog/5-heroic-tools-natural-language-processing/

#nlp #digest #libs

Top Machine Learning Open Source from August 2019

https://medium.com/@Mybridge/top-machine-learning-open-source-from-august-2019-8847e911b85a