The "Attention is all you need paper" that introduced Transformer neural network architecture has been around for roughly six years. It's by far the first architecture to maintain its universality for a long time, not just for a single modality but for other modalities as well.
MACHINE LEARNING
-
AI for IT Operations: Cloud Alerts, Incident Detection, Predictive Maintenance
By
–
#AI for IT Operations =
1) Cloud Spend Alerts
2) Early Incident Detection
3) Predictive Maintenance
***
#DeepLearning technology from @abacusai to the rescue! https://
abacus.ai/itoperations
———
#AIOps #MLOps #DevOps #BigData #DataScience #MachineLearning #PredictiveAnalytics #TimeSeries -
Mindbreeze Listed Among KMWorld’s Top 100 Knowledge Management Companies
By
–
.
@Mindbreeze is Listed Once Again Among @KMWorld
's Top 100 Companies That Matter in #KnowledgeManagement: https://
mindbreeze.com/mindbreeze-is-
listed-once-again-among-kmworlds-top-100-companies-that-matter-in-knowledge-management?ls=22
…
———
#InsightsDiscovery #Semantic #BigData #Analytics #DataScience #AI #MachineLearning #KnowledgeGraph #Knowledgebase #LinkedData #TextMining #GraphDB -
Join SAS Innovate 2023 Conference in Orlando May 8-10
By
–
Join @SASsoftware plus 1000+ other #AI and Data #Analytics business leaders, industry transformers, & technology experts at #SASInnovate 2023 in Orlando May 8-10. Register now and build your Agenda here: https://
sas.com/gms/redirect.j
sp?detail=PLN2755_1799220624
…
————
#DataScience #MachineLearning #ML #SASVisionary -
CNNs at Scale: How AlexNet Changed Machine Learning History
By
–
Many people were clearly using CNNs but history says Alex and his colleagues did it on large scale and the results transcended the field.
-
Embedding and Ranker Choices: Ada and kNN Performance Comparison
By
–
For science I also added:
– Choice of Embedding: simple tfidf bigrams or the OpenAI API embeddings ada-002 (ada should work better (?), tfidf is much much simpler)
– Choice of Ranker: kNN (much faster/simpler) or SVM
Default that seems to be both good & fast is ada+knn -
Linear Model Training with Sample Weights for Class Balance
By
–
didn't follow but sounds interesting. "train a linear model with sample weights to class balance"…?
-
Training SVMs on High-Dimensional Embeddings: Performance and Practical Considerations
By
–
yeah 😀 it's not as bad as it sounds, e.g. using the example in the notebook, training an SVM on ~10K 1536D embeddings is ~1 second. Sometimes it's possible to precompute. And sometimes it's just not worth it, all depends on setting / application.
-
How to Confuse Your Machine Learning Model
By
–
How to confuse your machine learning model. (credit: @teenybiscuit
) -
Research Community Loneliness: Building Networks Post-PhD
By
–
There's great communities for jr. researchers to get involved & alleviate this loneliness (eg @ml_collective @forai_ml @AiEleuther
) but may be harder for someone post-PhD, since they're supposed to be "independent." Is research community loneliness a problem? Is it fixable? 5/5