Catégorie : Notes
-
The Kano Model: Developing for Value and Delight – DZone Agile
https://dzone.com/articles/the-kano-model-developing-for-value-and-delight?utm_content=buffer44953&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
Awesome Tricks And Best Practices From Kaggle – KDnuggets
https://www.kdnuggets.com/2021/04/awesome-tricks-best-practices-kaggle.html
-
Dodrio – An interactive visualization system designed to help NLP researchers and practitioners analyze and compare attention weights in transformer-based models with linguistic knowledge.
https://github.com/poloclub/dodrio GitHub – poloclub/dodrio: Exploring attention weights in transformer-based models with linguistic knowledge. Dodrio . An interactive visualization system designed to help NLP researchers and practitioners analyze and compare attention weights in transformer-based models with linguistic knowledge. github.com
-
ringgaard/sling: SLING – A natural language frame semantics parser
https://github.com/ringgaard/sling
-
GokuMohandas/mlops: https://madewithml.com/
https://github.com/GokuMohandas/mlops
-
Nlp Cypher news
https://pub.towardsai.net/the-nlp-cypher-04-04-21-9964ab34df17?source=rss—-98111c9905da—4?source=social.tw
-
28 Free AI, Machine Learning, Data Science & Python eBooks
https://www.theinsaneapp.com/2020/11/free-machine-learning-data-science-and-python-books.html?_lrsc=48ff6393-3ae5-4534-aaa8-714a99fa18a2&m=1
-
AllenNLP Project Gallery
https://gallery.allennlp.org/
-
MAIF/shapash: Shapash makes Machine Learning models transparent and understandable by everyone
https://github.com/MAIF/shapash
-
GPT-Neo 2.7B
GPT-Neo 2.7B is a transformer model designed using EleutherAI’s replication of the GPT-3 architecture. GPT-Neo refers to the class of models, while 2.7B represents the number of parameters of this particular pre-trained model. This model is the same size as OpenAI’s "Ada" model. https://huggingface.co/EleutherAI/gpt-neo-2.7B EleutherAI/gpt-neo-2.7B · Hugging Face GPT Neo 2.7B. The GPT Neo model…
-
Word Mover’s Distance for Text Similarity
https://towardsdatascience.com/word-movers-distance-for-text-similarity-7492aeca71b0 Word Mover’s Distance for Text Similarity | by Nihit Saxena | Towards Data Science – Medium Introduction of the NLP (Natural Language Processing) revolutionized all the industries. So, NLP is a branch of AI (artificial Intelligence) that helps computer understand, interpret and manipulate human language. Now, with heaps of data available (thanks to big…
-
Google Brain Introduces Symbolic Programming + PyGlove Library to Reformulate AutoML | by Synced | Feb, 2021 | Medium
https://medium.com/@Synced/google-brain-introduces-symbolic-programming-pyglove-library-to-reformulate-automl-bde1d60cb8f6
-
The Best of NLP
https://cacm.acm.org/magazines/2021/4/251336-the-best-of-nlp/fulltext The Best of NLP | April 2021 | Communications of the ACM "Each time, the added scale gives us new capabilities to let us test new assumptions," Bosselut says. "As much as many people think we are going too far down this path, the truth is that the next iteration of language modeling could…
-
Yoshua Bengio Team Proposes Causal Learning to Solve the ML Model Generalization Problem | by Synced | SyncedReview | Mar, 2021 | Medium
https://medium.com/syncedreview/yoshua-bengio-team-proposes-causal-learning-to-solve-the-ml-model-generalization-problem-762c31b51e04
-
List of Top 5 Powerful Machine Learning Algorithms That Will Solve 99% of Your Problems
https://laconicml.com/machine-learning-algorithms/ List of Top 5 Powerful Machine Learning Algorithms | Laconicml Machine learning (ML) is the study of computer algorithms that improve automatically through experience. It is seen as a subset of artificial intelligence.. Machine learning algorithms build a mathematical model based on sample data, known as “training data”, in order to make predictions or…
-
GitHub – sickcodes/Docker-OSX: Run Mac in a Docker! Run near native OSX-KVM in Docker! X11 Forwarding! CI/CD for OS X!
https://github.com/sickcodes/Docker-OSX
-
Developing a Data-Driven Categorical Taxonomy of Emotional Expressions in Real World Human Robot Interactions | Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction
https://dl.acm.org/doi/10.1145/3434074.3447218
-
Quantum Mechanics, the Chinese Room Experiment and the Limits of Understanding
https://www.scientificamerican.com/article/quantum-mechanics-the-chinese-room-experiment-and-the-limits-of-understanding/
-
DeepMoji
https://medium.com/@bjarkefelbo/what-can-we-learn-from-emojis-6beb165a5ea0 https://github.com/bfelbo/DeepMoji bfelbo/DeepMoji State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc. – bfelbo/DeepMoji github.com
-
Keyword Assisted Topic Model • keyATM
https://keyatm.github.io/keyATM/
-
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
https://arxiv.org/abs/2005.11401 https://huggingface.co/transformers/master/model_doc/rag.html#tfragmodel "My biggest-challenge open-source collaboration with Huggingface : Tensorflow’s implementation of RAG (Retrieval Augmented Generation) is now available on Huggingface master !!! https://lnkd.in/gGVmw4X RAG ( https://lnkd.in/gdKWqqZ ) is an AI prototype that can read articles to give answers to any questions! With appropriate training data like ELI5 ( https://lnkd.in/gB4S4wj ) , it can even…
-
15 common mistakes data scientists make in Python (and how to fix them)
https://www.kdnuggets.com/2021/03/15-common-mistakes-python.html#.YD_fMYR72g0.linkedin 15 common mistakes data scientists make in Python (and how to fix them) – KDnuggets Writing Python code that works for your data science project and performs the task you expect is one thing. Ensuring your code is readable by others (including your future self), reproducible, and efficient are entirely different challenges that can…
-
Fast SMOTE upsampling with esmote
https://github.com/HMJiangGatech/ESmote GitHub – HMJiangGatech/ESmote: ESmote – An R package implemneting fast SMOTE algorithm esmote. esmote, an R package including fast SMOTE algorithm.. This is part of my undergraduate final year project. Which provide a really fast implementation of SMOTE algorithm. If you have any concerns please contact me: jianghm.ustc@gmail.com Some functions are still underconstruction. github.com
-
SMOTE for Imbalanced Classification with Python
https://machinelearningmastery.com/smote-oversampling-for-imbalanced-classification/ SMOTE for Imbalanced Classification with Python Imbalanced classification involves developing predictive models on classification datasets that have a severe class imbalance. The challenge of working with imbalanced datasets is that most machine learning techniques will ignore, and in turn have poor performance on, the minority class, although typically it is performance on the minority…
-
Way beyond AlphaZero: Berkeley and Google work shows robotics may be the deepest machine learning of all | ZDNet
https://www.zdnet.com/article/way-beyond-alphazero-berkeley-and-google-work-shows-robotics-may-be-the-deepest-machine-learning-of-all/?utm_content=buffere4883&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer
-
GitHub – MaartenGr/BERTopic: Leveraging BERT and c-TF-IDF to create easily interpretable topics.
https://github.com/MaartenGr/BERTopic
-
GitHub – MaartenGr/BERTopic: Leveraging BERT and c-TF-IDF to create easily interpretable topics.
https://github.com/MaartenGr/BERTopic
-
98 things that can go wrong in an ML project
https://towardsdatascience.com/51-things-that-can-go-wrong-in-a-real-world-ml-project-c36678065a75
-
NLP Text-Classification in Python: PyCaret Approach Vs The Traditional Approach
https://towardsdatascience.com/nlp-classification-in-python-pycaret-approach-vs-the-traditional-approach-602d38d29f06 NLP Text-Classification in Python: PyCaret Approach Vs The Traditional Approach | by Prateek Baghel | Towards Data Science I. Introduction. In this post we’ll see a demonstration of an NLP-Classification problem with 2 different approaches in python: 1-The Traditional approach: In this approach, we will: – preprocess the given text d ata using different…
-
Classifying emotions using audio recordings and Python
The theory of Sound and Acoustics could be used for cutting edge Emotion-Recognition technologies. here’s how we can apply it using Python https://towardsdatascience.com/classifying-emotions-using-audio-recordings-and-python-434e748a95eb
-
Intel Gives Scikit-Learn the Performance Boost Data Scientists Need
Scikit-learn is one of the most widely used Python packages for data science and machine learning (ML). Scikit-learn accelerators can analyze ML data across many industry use-cases while driving efficient use of hardware resources. The Intel optimizations for scikit-learn, made available through Intel AI Analytics Toolkit, reduce run times and gives data scientists time back…
-
Cluster Documents Using Word2Vec
https://datamuni.com/@dylanjcastillo/cluster-documents-using-word2vec DataMuni: Cluster Documents Using Word2Vec These are the libraries you need for the sample project. Here’s what you do with each of them: **os** and **random** help you define a random seed to make the code deterministically reproducible. **re** and **string** provide you with easy ways to clean the data. **pandas**helps you read the…
-
SEO Turns to Data Graphs to Learn About the Web – Go Fish Digital
https://gofishdigital-com.cdn.ampproject.org/c/s/gofishdigital.com/data-graph/amp/
-
22 February, 2021 07:21
https://github.com/huggingface/transformers/tree/master/examples/research_projects/zero-shot-distillation
-
Vowpal Wabbit
https://vowpalwabbit.org/
-
Class Imbalance: Random Sampling and Data Augmentation with Imbalanced-Learn
https://towardsdatascience.com/class-imbalance-random-sampling-and-data-augmentation-with-imbalanced-learn-63f3a92ef04a Class Imbalance: Random Sampling and Data Augmentation with Imbalanced-Learn | by Fernando López | Feb, 2021 | Towards Data Science One of the challenges that arise when developing machine learning models for classification is class imbalance. Most of the machine learning algorithms for classification were developed assuming… towardsdatascience.com
-
CTrL and MNTDP, a new open source benchmark and model for continual learning
https://ai.facebook.com/blog/ctrl-and-mntdp-a-new-open-source-benchmark-and-model-for-continual-learning/
-
19 February, 2021 07:13
https://towardsdatascience.com/7-models-on-huggingface-you-probably-didnt-knew-existed-f3d079a4fd7c
-
2021 Social Media Industry Benchmark Report | Rival IQ
https://www.rivaliq.com/blog/social-media-industry-benchmark-report/
-
14 free or affordable online courses to learn Python, offered by MIT, Harvard, UPenn, Google, and more
https://www.businessinsider.com/how-to-learn-python?_lrsc=eda1cd61-8077-4229-8cb0-1e997906fb46#learning-python-3 14 free or affordable online courses to learn Python, offered by MIT, Harvard, UPenn, Google, and more Python is one of the most popular programming languages used in everything from data analysis to AI. Here are some of the best classes to learn it. www.businessinsider.com
-
Beyond 512 Tokens
https://research.google/pubs/pub49617/
-
Python Concurrency: The Tricky Bits –
https://python.hamel.dev/concurrency/
-
14 February, 2021 21:50
https://github.com/kakaobrain/pororo GitHub – kakaobrain/pororo: Pororo: A Deep Learning based Multilingual Natural Language Processing Library Pororo: A Deep Learning based Multilingual Natural Language Processing Library. Pororo performs Natural Language Processing and Speech-related tasks.. It is easy to solve various subtasks in the natural language and speech processing field by simply passing the task name. github.com
-
Ready to start coding? What you need to know about Python – TechRepublic
https://www-techrepublic-com.cdn.ampproject.org/c/s/www.techrepublic.com/google-amp/article/ready-to-start-coding-what-you-need-to-know-about-python/
-
Visualizing the effect of hyperparameters on Support Vector Machines | by Carlos Domnguez Garca | Feb, 2021 | Towards Data Science
https://towardsdatascience.com/visualizing-the-effect-of-hyperparameters-on-support-vector-machines-b9eef6f7357b
-
How we sped up transformer inference 100x for 🤗 API customers
https://huggingface.co/blog/accelerated-inference
-
Doccano – An open-source text annotation tool for humans.
An open-source text annotation tool for humans. Annotation features for : Text classification Sequence labeling Sequence to sequence tasks. Label data for: sentiment analysis, named entity recognition, text summarization and … Features: Collaborative annotation Multi-language support Mobile support Emoji 😄 support Dark theme RESTful API pip install doccano https://github.com/doccano/doccano GitHub – doccano/doccano: Open source text…
-
Open GPU Data Science | RAPIDS
https://rapids.ai/