AI 学习中心
按入门与选型、游戏开发、图像与3D、视频与音频、智能体与自动化、模型与工程六个主题学习。站内文章提供示例与检查方法，外部资料保留原文入口。
- Generalized Language Models
[Updated on 2019-02-14: add ULMFiT and GPT-2.] [Updated on 2020-02-29: add ALBERT.] [Updated on 2020-10-25: add RoBERTa.] [Updated on 2020-12-13: add T5.] [Updated on 2020-12-30: add GPT-3.] [Updated …
- Are Deep Neural Networks Dramatically Overfitted?
[Updated on 2019-05-27: add the section on Lottery Ticket Hypothesis.] If you are like me, entering into the field of deep learning with experience in traditional machine learning, you may often ponde…
- Domain Randomization for Sim2Real Transfer
In Robotics, one of the hardest problems is how to make your model transfer to the real world. Due to the sample inefficiency of deep RL algorithms and the cost of data collection on real robots, we o…
- Meta Reinforcement Learning
In my earlier post on meta-learning, the problem is mainly defined in the context of few-shot classification. Here I would like to explore more into cases when we try to “meta-learn” Reinforcement Lea…
- Evolution Strategies
Stochastic gradient descent is a universal choice for optimizing deep learning models. However, it is not the only option. With black-box optimization algorithms, you can evaluate a target function $f…
- The Transformer Family
[Updated on 2023-01-27: After almost three years, I did a big refactoring update of this post to incorporate a bunch of new Transformer models since 2020. The enhanced version of this post is here: Th…
- Exploration Strategies in Deep Reinforcement Learning
[Updated on 2020-06-17: Add “exploration via disagreement” in the “Forward Dynamics” section. Exploitation versus exploration is a critical topic in Reinforcement Learning. We’d like the RL agent to f…
- Neural Architecture Search
Although most popular and successful model architectures are designed by human experts, it doesn’t mean we have explored the entire network architecture space and settled down with the best option. We…
- How to Build an Open-Domain Question Answering System?
[Updated on 2020-11-12: add an example on closed-book factual QA using OpenAI API (beta). A model that can answer any question with regard to factual knowledge can lead to many useful and practical ap…
- Controllable Neural Text Generation
[Updated on 2021-02-01: Updated to version 2.0 with several work added and many typos fixed.] [Updated on 2021-05-26: Add P-tuning and Prompt Tuning in the “prompt design” section.] [Updated on 2021-0…
- Reducing Toxicity in Language Models
Large pretrained language models are trained over a sizable collection of online data. They unavoidably acquire certain toxic behavior and biases from the Internet. Pretrained language models are very…
- Contrastive Representation Learning
The goal of contrastive representation learning is to learn such an embedding space in which similar sample pairs stay close to each other while dissimilar ones are far apart. Contrastive learning can…
- What are Diffusion Models?
[Updated on 2021-09-19: Highly recommend this blog post on score-based generative modeling by Yang Song (author of several key papers in the references)]. [Updated on 2022-08-27: Added classifier-free…
- How to Train Really Large Models on Many GPUs?
[Updated on 2022-03-13: add expert choice routing.] [Updated on 2022-06-10]: Greg and I wrote a shorted and upgraded version of this post, published on OpenAI Blog: “Techniques for Training Large Neur…
- Learning with not Enough Data Part 3: Data Generation
Here comes the Part 3 on learning with not enough data (Previous: Part 1 and Part 2). Let’s consider two approaches for generating synthetic data for training. Augmented data. Given a set of existing …
- Generalized Visual Language Models
Processing images to generate text, such as image captioning and visual question-answering, has been studied for years. Traditionally such systems rely on an object detection network as a vision encod…
- Some Math behind Neural Tangent Kernel
Neural networks are well known to be over-parameterized and can often easily fit data with near-zero training loss with decent generalization performance on test dataset. Although all these parameters…
- Large Transformer Model Inference Optimization
[Updated on 2023-01-24: add a small section on Distillation.] Large transformer models are mainstream nowadays, creating SoTA results for a variety of tasks. They are powerful but very expensive to tr…