4. MonkeyLearn It allows you to create custom machine learning models without coding. → Sentiment analysis
→ Text classification
→ Keyword extraction
→ Topic classification Reduce your workload further by automating tasks that require sophisticated analysis.
MACHINE LEARNING
-
MonkeyLearn: create custom ML models without coding
By
–
-
Optimizing LLM Training: Data Mixture Best Practices
By
–
The results from training LLMs can be drastically different depending on the data input mixtures. How do you optimize for the best results? pic.twitter.com/EKSii0ffR3
— Replit ⠕ (@Replit) 9 août 2023The results from training LLMs can be drastically different depending on the data input mixtures. How do you optimize for the best results?
-
Hidden Cloud Training Costs in AI: On-Premises Solution
By
–
Costs in the AI age? Thomas Robinson of @DominoDataLab warns about hidden cloud training costs in @ForbesTech
. On-premises training could be the key. Every penny counts. Turn to Domino to scale #AI wisely. https://
domino.buzz/44Xxowx #MachineLearning #EnterpriseAI #CostEfficiency -
LLM Capability and Reliability: Orthogonal Vectors
By
–
This. is. so. true. #LLMs are great – Remember the vectors of capability and reliability and they are often orthogonal. It's true with people as well.
-
Instruction Tuning Risks When Models Lack Training Data Knowledge
By
–
Glad to see this work on alignment; an interesting takeaway for me here is that instruction tuning on data that the model doesn't know can be really, really bad. Basically when you finetune on data the model doesn't know, in addition to teaching it that particular training
-
VRDU: Visual Rich Document Understanding Benchmark Dataset
By
–
Presenting Visually Rich Document Understanding (VRDU), a dataset for better tracking of document understanding task progress. Read about VRDU and the five requirements needed to create benchmarks that capture the complexity of real-world applications → https://t.co/YQsKii17WD pic.twitter.com/oaGB3yzxwX
— Google AI (@GoogleAI) 9 août 2023Presenting Visually Rich Document Understanding (VRDU), a dataset for better tracking of document understanding task progress. Read about VRDU and the five requirements needed to create benchmarks that capture the complexity of real-world applications → https://
bit.ly/3KApkJU -
Foundation Models: Data-Centric Techniques for Business Quality
By
–
5/ Foundation models are great, but they're just a foundation. For business-critical applications where quality matters, use the full slate of data-centric model improvement techniques!
-
DistilBERT Fine-Tuning Achieves 84 F1 With Programmatic Labeling
By
–
4/ For maximum quality, we finished with fine-tuning, using Snorkel Flow to programmatically label data in areas where the model was still underperforming. Our best model (~84 F1) is fine-tuned DistilBERT, a model 10,000x smaller than GPT-4.
-
Perspectives on Diffusion Models in AI and Machine Learning
By
–
Perspectives on diffusion https://
bit.ly/45nzZjn #AI #MachineLearning #DeepLearning #LLMs #DataScience -
SAS Explore Vegas: Analytics and AI Solutions Event Sept
By
–
We are making smart bets in Vegas at SAS Explore . See the power of analytics & SAS solutions at #ExploreSAS—the hands-on user event to be up close and in-person for. Our exclusive Innovation Hub and more awaits http://
2.sas.com/6014PeTCy #MachineLearning #AI | Sept. 11-14