Connecting Scholarly Communications
Joined May 2014
- Tweets 231
- Following 8
- Followers 66
- Likes 6
5 Photos and videos
Research Graph retweeted
13 Nov 2023
RAG: Supercharging AI with Smart Data Retrieval aigraph.researchgraph.org/20…
1
65
Platform to assess applications to access sensitive data. Safe person? Correct data for correct project?
youtu.be/BbT_3qyeDM0?si=wub7…
1
2
83
Research Graph retweeted
7 Nov 2023
Great to see Reproducible Outputs as one of the new functions of GPT-4 platform.openai.com/docs/gui… #gpt #artificalintelligence
1
67
Research Graph retweeted
6 Nov 2023
15 New Initiatives in the New White House Order on AI
aigraph.researchgraph.org/20…
1
60
While they are effective in understanding and generating natural language, they have limitations such as producing incorrect responses, known as the hallucination effect. This can lead to potential risks in clinical settings, especially in areas like imaging appropriateness
1
23
Large language models (LLMs) like ChatGPT, developed by OpenAI, have shown success in various tasks due to their advanced architecture and training mechanisms.
#aigraph
pubs.rsna.org/doi/10.1148/ra…
1
1
57
Research Graph retweeted
27 Oct 2023
Mistral AI is 187x cheaper compared to GPT-4
aigraph.researchgraph.org/20…
1
1
79
Research Graph retweeted
22 Oct 2023
Feature engineering refers to the process of creating new input variables from the available data. #aigraph
machinelearningmastery.com/d…
1
22
Research Graph retweeted
22 Oct 2023
data preparation can be treated as another hyperparameter to tune as part of the modeling pipeline.
machinelearningmastery.com/f…
1
21
Research Graph retweeted
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
Google Bard will destroy ChatGPT because it’s a long-term game, and Google has the upper hand in terms of market dominance. ChatGPT has a better product, but that doesn’t mean they’ll win the long race.
#aigraph medium.com/@alanany/the-chat…
1
36
This post details how to apply three core UX concepts to generative AI products: 1) affordances, 2) feedback, and 3) constraints.
#aigraph
towardsdatascience.com/the-d…
1
1
27
Research Graph retweeted
18 Oct 2023
Engineers can now test models without worrying about privacy concerns since generative AI can produce large amounts of synthetic data that mirrors real-world information
#aigraph
towardsdatascience.com/5-gen…
1
1
49
Large language models have found applications in a wide range of fields, transforming the way we interact with technology and enabling new possibilities, including NLP, Chatbots and virtual assistants, automation, Language translation, etc.
#aigraph
indatalabs.com/blog/large-la…
1
29
Research Graph retweeted
19 Oct 2023
Dimensionality reduction results in fewer input variables which allows for a simpler predictive model that may have better performance when making predictions on new data.
#aigraph
machinelearningmastery.com/l…
1
42
The output of the OCR process is a text that contains typos, recognition mistakes, non-text symbols, and other inaccuracies.
Another challenge that machine learning engineers face is what to define as a word like Chinese, Japanese, or Arabic.
#aigraph
indatalabs.com/blog/nlp-chal…
1
56
Research Graph retweeted
8 Oct 2023
LLMs cannot understand written text directly, so Sentence Embedding is carried out. Thanks to the large dimension of the vector created by embedding, small variations in the data can be seen with greater precision.
#aigraph
towardsdatascience.com/maste…
1
1
59
With just a simple, but powerful calculation like the Cosine Similarity, we can build a reasonable recommendation system.
#aigraph
towardsdatascience.com/what-…
1
16
Research Graph retweeted
3 Oct 2023
Applying LLM on the keyword research will be a revolution of seo. #aigraph
techopedia.com/12-practical-…
2
2
32
LLMs have many specific types.
Autoregressive language models, Transformer-based models, Encoder-decoder models, Pre-trained and fine-tuned models, Multilingual models, and Hybrid models. For instance, LLaMa2 we are using is transformer-based.
#aigraph
spiceworks.com/tech/artifici…
1
40