Artificial Intelligience

This post gives a gentle introduction to Task and Motion Planning (TAMP).

This post gives a gentle introduction to the diffusion models, a family of the state of art generative model.

This post gives a gentle introduction to the neural models used in NLP in recent years, which sees a trend from sequence models (RNN, GRU, LSTM), to attention-based models (transformers).

This post introduces some methods to create vector embeddings for words that are/were widely used - Skip-Gram, CBOW, and GloVe.

This post serves as an introduction to some basic deep reinforcement learning methods including policy gradients, actor-critic, and deep Q-network, and a Pytorch implementation of the methods.