YunLearnAI

[YunLearnAI @YunLearnAI]

Transformers, introduced in 2017, are a pivotal architecture for LLMs, designed around the concept of attention, which helps process longer text sequences efficiently

https://t.co/lQLz92QFDy
#LLM #NLP

[YunLearnAI @YunLearnAI]

data preparation can be treated as another hyperparameter to tune as part of the modeling pipeline.

https://t.co/Fbhsghd5wD

[YunLearnAI @YunLearnAI]

Feature engineering refers to the process of creating new input variables from the available data. #aigraph
https://t.co/UC3m6J08Pi

[YunLearnAI @YunLearnAI]

LLMs enhance conversational AI: Large Language Models (LLMs) have significantly improved the quality and scalability of conversational AI applications across various industries and use cases.
#LLM #aigraph

https://t.co/sufZ0PEiKm

[YunLearnAI @YunLearnAI]

Applying LLM on the keyword research will be a revolution of seo. #aigraph

https://t.co/5LHqIWXlbM

[OpenAI @OpenAI]

ChatGPT can now browse the internet to provide you with current and authoritative information, complete with direct links to sources. It is no longer limited to data before September 2021.

[YunLearnAI @YunLearnAI]

if one clustering algorithm performs better than other clustering algorithms on many of these measures, then we can have some confidence that it is truly the best clustering algorithm.
#evaluation #criteria #entropy #F-measure #overall-similarity #algraph
https://t.co/fhrbM0qSBJ

[YunLearnAI @YunLearnAI]

it does a great job of seeking areas in the data that have a high density of observations, versus areas of the data that are not very dense with observations. DBSCAN can sort data into clusters of varying shapes as well

https://t.co/f8zMJ1Un4A

#DBSCAN #aigraph

[YunLearnAI @YunLearnAI]

A comprehensive study. Algorithmic bias, privacy concerns, and copyright infringement are discussed.

https://t.co/DHSlxb1q00

#social #legal #bias

[YunLearnAI @YunLearnAI]

https://t.co/rYcODusAYa

#citation #LLM #aigraph

these citations also establish connections among sci-entific papers, providing high-quality inter-document relationships and human-constructed knowledge.

[YunLearnAI @YunLearnAI]

BERT’s secret sauce lies in its ability to understand the bidirectional context.

https://t.co/q0vqiiYT9L

[YunLearnAI @YunLearnAI]

https://t.co/gJPjEtiDqx

In the case of BERT, the model is trained to predict one word for the corresponding mask. But T5 is hybrid. It is trained to output one word or multiple words for one mask

[YunLearnAI @YunLearnAI]

Euclidean distance is sensitive to the magnitudes of the vectors, whereas cosine similarity is not.

https://t.co/hXY4jv6BvS

[YunLearnAI @YunLearnAI]

Imagine islands on the ocean, where the sea level is the threshold and the different islands are your clusters. The land below the sea level is noise. As the sea level goes down, new islands appear some islands combine to form bigger island
#aigraph

https://t.co/FEdLeW4Wdg

[YunLearnAI @YunLearnAI]

the proposed HAC ultilize the information of the algorithm, reduce the unnecessary computation.

Used unsupervised classification accuracy (confusion matrix) to measure the performance. It' s quite intuitive and reasonable.
#aigraph

https://t.co/SJxOMngw9K

[YunLearnAI @YunLearnAI]

Use grant-to-article to validate the unsupervised task. It might be a potential metric that we can apply on our clustering. #aigraph
https://t.co/jQ8kf0769x

[YunLearnAI @YunLearnAI]

Comparison of 4 types of clustering algorithm

https://t.co/fgRhSlhpJ3

#aigraph

[YunLearnAI @YunLearnAI]

LDA idea is simple but math background is quite complicated. 😪😪

https://t.co/5mYiyvh3Ff

#aigraph

[YunLearnAI @YunLearnAI]

Simultaneously leans feature representation and cluster assignments!

https://t.co/xLepOhy7de

[YunLearnAI @YunLearnAI]

Fine tuning + clustering: from the perspective of optimization
https://t.co/Argl1bisMB