Aishwarya Nambissan (@AishLearnsAI) profile picture
Joined July 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
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
Reinforcement learning with human feedback is a possible means of addressing harmful biases in language models. #aigraph doi.org/10.48550/arXiv.2102.…
1
1
22
The Deep Feature-Based Text Clustering is based on a deep pretrained model that can construct the meaning of words by contextual information, avoiding the processing of high-dimensional sparse features. #aigraph ieeexplore.ieee.org/document…
2
53
Hierarchical clustering has high space and time complexity. So, this clustering algorithm cannot be used for large datasets. #aigraph towardsdatascience.com/under…
1
27
AI technology has the potential to improve workplace safety and efficiency by analyzing task completion patterns. Hyundai and Mercedes-Benz are using AI embedded in exoskeletons to help human workers to perform most repetitive tasks better. #aigraph doi.org/10.1016/j.jbusres.20…
1
28
The memory requirements for Llama-2 does not make it a feasible option for researchers to use on their own systems. Petals is a potential alternative as it provides access to public servers that researchers can use for their LLMs. #aigraph pub.aimind.so/this-is-why-yo…
1
32
Subject classification is done to help combine resources by subject, but it is done manually since it requires a lot of training. Automated subject classification techniques are now introduced: upstream.force11.org/attempt… #aigraph
1
30
Sentence transformers are LLMs that are specially trained to output embeddings at the sentence level rather than the word or token level. These sentence level embeddings do a better job of capturing meaning and are far quicker to compute. #aigraph medium.com/@swansburg.justin…
1
33
Instruction Tuning and Reinforcement Learning with Human Feedback are 2 training steps that were applied to ChatGPT to make it work so well. #aigraph mark-riedl.medium.com/a-very…
1
45