The Python, AI & Data series goes from collecting and cleaning data to machine learning, deep learning, Vietnamese language processing, LLMs, RAG, agents and running models in production, with runnable Python code ...
LLMs (large language models) look like a person answering questions, but at their core they do one thing: they look at the sequence of tokens so far and estimate the probability of the next token. Onc...
Invoices, official papers, scanned minutes and phone photos are still the largest body of data that businesses have not managed to get into their systems. OCR (optical character recognition) turns an...
Turning speech into text is a familiar problem for businesses: call-center recordings, meeting minutes, subtitles for tutorial videos. Since late 2022, OpenAI's Whisper has made it something you can r...
A store gets thousands of customer reviews every month, and the usual question is how many of them are complaints. This task is called sentiment analysis, and for Vietnamese the popular choice today i...
Almost every language model you hear about today, from BERT and PhoBERT to text-generation models, is built on the same architecture: the Transformer. This article does not argue which model is "smart...
In the previous article, TF-IDF treated "ô tô" and "xe hơi" (two Vietnamese words for "car") as two completely separate columns: nothing says they mean almost the same thing. The model only knows the...
A news site receives several hundred stories a day and must file each one under the right section. An online store has to sort customer feedback into "delivery", "payment" or "warranty". Both are text...
A store wants to know how many bottles, cans and cartons are left on a shelf, and where they sit. The image classifier from the previous article only answers "which class is this image?", but inventor...
You have 244 training images, two classes (ants and bees), and you want an image classifier. Training a CNN from scratch gives 71.9% on the validation set (153 images: 70 ants, 83 bees, so always gues...
Getting a neural network to run once does not mean you know how to do deep learning training reliably. Change the learning rate from 0.001 to 0.1, with the same model and the same data, and accuracy c...
Frameworks like PyTorch let you train neural networks in a few lines, but when the loss stops falling or the gradients vanish, you can't tell where to start unless you understand what happens inside....
In earlier articles we wrote gradient descent by hand with NumPy: derivatives worked out on paper, updates applied manually. That approach teaches the fundamentals, but it breaks down once a model has...
All articles are displayed
