Joined July 2023
- Tweets 32
- Following 7
- Followers 4
- Likes 5
1 Photos and videos
22 Oct 2023
Transformers, introduced in 2017, are a pivotal architecture for LLMs, designed around the concept of attention, which helps process longer text sequences efficiently
developers.google.com/machin…
#LLM #NLP
1
31
22 Oct 2023
data preparation can be treated as another hyperparameter to tune as part of the modeling pipeline.
machinelearningmastery.com/f…
1
21
22 Oct 2023
Feature engineering refers to the process of creating new input variables from the available data. #aigraph
machinelearningmastery.com/d…
1
22
8 Oct 2023
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
towardsdatascience.com/redef…
1
17
3 Oct 2023
Applying LLM on the keyword research will be a revolution of seo. #aigraph
techopedia.com/12-practical-…
2
2
32
28 Sep 2023
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
stat.cmu.edu/~rnugent/PCMI20…
1
23
27 Sep 2023
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
elutins.medium.com/dbscan-wh…
#DBSCAN #aigraph
1
23
25 Sep 2023
A comprehensive study. Algorithmic bias, privacy concerns, and copyright infringement are discussed.
towardsdatascience.com/the-p…
#social #legal #bias
1
3,122
25 Sep 2023
paperswithcode.com/paper/whe…
#citation #LLM #aigraph
these citations also establish connections among sci-entific papers, providing high-quality inter-document relationships and human-constructed knowledge.
1
35
21 Sep 2023
BERT’s secret sauce lies in its ability to understand the bidirectional context.
medium.com/@shaikhrayyan123/…
1
22
20 Sep 2023
medium.com/@zaiinn440/a-comp…
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
9
11 Sep 2023
Euclidean distance is sensitive to the magnitudes of the vectors, whereas cosine similarity is not.
medium.com/@swansburg.justin…
1
25
7 Sep 2023
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
towardsdatascience.com/a-gen…
1
15
29 Aug 2023
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
arxiv.org/abs/1301.7401
1
41
29 Aug 2023
Use grant-to-article to validate the unsupervised task. It might be a potential metric that we can apply on our clustering. #aigraph
journals.plos.org/plosone/ar…
1
25
28 Aug 2023
Comparison of 4 types of clustering algorithm
researchgate.net/publication…
#aigraph
1
26
22 Aug 2023
LDA idea is simple but math background is quite complicated. 😪😪
scopus.com/record/display.ur…
#aigraph
25
16 Aug 2023
Simultaneously leans feature representation and cluster assignments!
arxiv.org/abs/1511.06335
1
34
15 Aug 2023
Fine tuning clustering: from the perspective of optimization
aclanthology.org/2020.coling…
1
23