Welcome!
  Post Categories
data science 121 search 1 data engineering 181 machine learning 6 optimization 3 Metaverse 1 physics 3 stack overflow 1 image processing 3 algorithm 13 VR 1 fintech 7 web3 1
The Power of Open Source LLMs, Empowering Private Conversations and Enhanced Chatbot Capabilities The Power of Open Source LLMs, Empowering Private Conversations and Enhanced Chatbot Capabilities
In today’s digital landscape, safeguarding our data and maintaining control over our interactions has become increasingl
2023-06-28 data science
large language model
Understanding Transformer Models in Deep Learning, Explaining with Salience Maps Understanding Transformer Models in Deep Learning, Explaining with Salience Maps
Deep learning models, especially transformer models, have achieved remarkable success in various natural language proces
2023-06-27 data science
pytorch explainability
Understanding Convolution, From Mathematics to Image Processing Understanding Convolution, From Mathematics to Image Processing
Convolution is a powerful mathematical operation that plays a crucial role in various fields, including signal processin
2023-06-26 data science
convolution
How to evaluate and visualize regression results How to evaluate and visualize regression results
When evaluating regression models, there are several metrics you can use to assess their performance beyond just Mean Sq
2023-06-24 data science
regression
Understanding Loss Functions, Backpropagation, and the PyTorch Transformer Understanding Loss Functions, Backpropagation, and the PyTorch Transformer
In the field of deep learning, loss functions and the backpropagation algorithm play a crucial role in training neural n
2023-06-22 data science
deep learning loss function backpropagation
Fast way to map an array X and array Y using nonparametric regression, a decision tree based regression Fast way to map an array X and array Y using nonparametric regression, a decision tree based regression
If want to find a a non linear relationship between two arrays, and it’s hard to model it using simple functions such as
2023-06-19 data science
regression descion tree
Utilizing Human Feedback for Enhanced Fine-Tuning of Large Language Models, RLHV vs finetuning difference Utilizing Human Feedback for Enhanced Fine-Tuning of Large Language Models, RLHV vs finetuning difference
Wonder what’s the difference between RLHF method with finetuning method? Fine-Tuning is actually the first step of a RL
2023-06-17 data science
finetuning RLHF
Constraining Prediction ranges in Deep Learning Regression Models Constraining Prediction ranges in Deep Learning Regression Models
Deep learning is widely used for various regression analysis tasks. However, sometimes we need to apply certain constrai
2023-06-16 data science
deep learning regression
New Function role added to GPT3.5 and GPT4 to give model to use API or functions as tools New Function role added to GPT3.5 and GPT4 to give model to use API or functions as tools
The latest update (June 2023) from OpenAI added a new role called function into their tool box.By describing functions i
2023-06-15 data science
chatgpt openai gpt4
The short history of open source large language model from chatGPT so far The short history of open source large language model from chatGPT so far
Large language models (LLMs) have revolutionized the field of artificial intelligence, and their long-lasting impact is
2023-06-13 data science
large language model
How critical is to normalize the input data, since there is layer normlization in the transformer encoder already How critical is to normalize the input data, since there is layer normlization in the transformer encoder already
Normalizing input data is generally a good practice, as it can improve the convergence rate and the overall performance
2023-06-11 data science
pytorch transformer
Input dimension for pytorch transformer when the sequence length is one Input dimension for pytorch transformer when the sequence length is one
In pytorch, when we want to provide a 2-dimensional input with shape (batch_size, embedding_size), we should be careful
2023-06-11 data science
pytorch transformer
4 / 11