RSSAmplifier

Blog

Tung M Phung's Blog

tungmphung.comRSS feed ↗20 posts

Latest posts

Plan More, Debug Less: Applying Metacognitive Theory to AI-Assisted Programming Education

The rise of AI in education offers exciting new ways to support student learning, especially in complex fields like programming. But simply using AI to generate feedback isn’t enough. To truly help students, we need to ground AI-driven tools in solid teaching principles. In our recent research, we explored how metacognition – the ability to understand and manage one’s own learning – can be used to…

Is ChatGPT as good as humans? A study in the field of programming education

How far is ChatGPT from Artificial General Intelligence? A recent study compares ChatGPT's performance to human for programming education.

Advanced (yet simple) Prompt Engineering techniques for Large Language Models

Advanced (yet simple) prompt engineering methods that are proven to work well in various domains.

Conversational AI: ChatGPT alternatives and their advantages

ChatGPT is not the only AI that can converse naturally with humans. In this article, we introduce alternatives for ChatGPT with their unique advantages.

Book Review: Problem Solving 101 by Ken Watanabe

A book that offers one simple approach to solving any problem.

Yes, we can now make ChatGPT as good as human tutors for programming education

A straightforward technique that significantly enhances ChatGPT's hint generation capabilities, placing it on par with expert human tutors for programming education.

Case study: Machine Learning and Deep Learning for Knowledge Tracing in Programming Education

Applying Machine Learning and Deep Learning to solve the Knowledge Tracing problem in the context of Programming classrooms.

Transforming everything to vectors with Deep Learning: from Word2Vec, Node2Vec, to Code2Vec and Data2Vec

Let us discuss the state-of-the-art methods for transforming every kind of input data into fixed-length vectors of continuous values, including Word2Vec, Doc2Vec, Image2Vec, Node2Vec, Edge2Vec, Code2Vec, and Data2Vec.

Reinforcement Learning approaches for the Join Optimization problem in Database: DQ, ReJoin, Neo, RTOS, and Bao

How can we use Reinforcement Learning for the problem of Join optimization in Database? Let us take a look at the 5 recent and outstanding approaches from top researchers in the world: DQ, ReJoin, Neo, RTOS, and Bao.

A review of pre-trained language models: from BERT, RoBERTa, to ELECTRA, DeBERTa, BigBird, and more

Let us review a list of pretrained language models, including BERT, Transformer-XL, XLNet, RoBERTa, DistilBERT, ALBERT, BART, ELECTRA, ConvBERT, DeBERTa, and BigBird.

Database questions & answers

A list of essential Database questions and answers to refresh your knowledge in this field.

Object-Oriented Programming questions & answers

This blog post lists some critical questions and answers about Object-oriented programming.

Networking basic questions & answers

A list of basic but practical questions & answers in the field of Networking.

Operating Systems questions & answers

A list of questions and answers to refresh your knowledge about Operation Systems.

A summary of modern C++ features

This blog post summarizes the main features of modern C++ from the developer's point of view. A must-read if you are preparing for an interview.

Pythonic Python

A pool of unique features in the Python programming language. A must read if you are preparing for an interview.

Reinforcement learning: Q Learning, Deep Q Learning introduction with Tensorflow

Q Learning, Deep Q Learning, Double Q Learning, and Dueling Q Learning explained. TensorFlow code provided.

On ensuring fairness: Statistical parity vs Causal graphs

We tackle the problem of ensuring fairness in machine learning, from using the traditional statistical parity to exploiting a causal network.

Subgroup Discovery: Beyond coverage and mean-shift

An outstanding subgroup might need more than just a big size and a difference average value from the population.

Some thoughts regarding Deep Learning’s achievements, hype, and challenges

A critical view of Deep Learning.