PinnedJonathan HuiA listing of my articles in deep learningIncludes object detection, self-driving car, meta-learning etc …3 min read·Apr 19, 2018--13--13
Jonathan HuiWhat is new with GPT-4?On March 14th, GPT-4 was released. It gave us some insight into its progress toward achieving superhuman proficiency. Nonetheless, you may…6 min read·Mar 15, 2023--1--1
Jonathan HuiHow much do I like ChatGPT?Andy Rachleff, an entrepreneur and investor, famously said that you know you have a strong product-market fit when your customers are so…12 min read·Jan 12, 2023--3--3
Jonathan HuiRL — Reinforcement Learning Algorithms OverviewWe have examined many Reinforcement Learning (RL) algorithms in this series, for instance, Policy Gradient methods for the MoJoCo tasks…8 min read·Dec 12, 2022--1--1
Jonathan HuiRL — Transfer Learning (Learn from the Past)Humans are explorers and we do it smartly. In reinforcement learning RL, model-free methods search the solution space millions of times…8 min read·Jun 27, 2022----
Jonathan HuiRL — PLATO Policy Learning using Adaptive Trajectory OptimizationImitation plays a major role in learning. In RL, it reduces the amount of time in searching for solutions and it is sample efficient. And…3 min read·May 10, 2022--1--1
Jonathan HuiRL — PredictionHow can we learn better? This is something we struggle with in real life also. Besides meta-learning, humans make predictions. Even if we…9 min read·Apr 26, 2022----
Jonathan HuiRL — Transfer LearningWe learn from past experiences. We apply learned knowledge to solve new tasks. In Deep Learning, training a deep network takes a lot of…8 min read·Apr 18, 2022----