Become a member
Sign in
Fan Zheng
Fan Zheng

Fan Zheng

32 Following
26 Followers
  • Profile

  • Claps

  • Highlights

Highlighted by Fan Zheng

See more

From Reinforcement Learning from scratch by Emmanuel Ameisen

ate our Q func…o an estimated reward, called the Q function. First, we’ll initialize all Q values at equal values. Then, we’ll update the Q value of each action (picking each chest) based on how good the payout was after choosing this action. This allows us to learn a good value function. We will approximate our Q function using a neural ne…

From Understanding Hinton’s Capsule Networks. Part II: How Capsules Work. by Max Pechyonkin

…ined using “dynamic routing”, which is a novel way to determine where each capsule’s output goes. I will dedicate a separate post to this algorithm and only offer some intuition here.

From Intuition Machines versus Algebraic Minds by Carlos E. Perez

…ement for a moment. In the NLP are that employs Deep Learning, recognition engines that incorporate semantic networks have shown to have better performance than ones that do not.

Claps from Fan Zheng

See more

Support Vector Regression Or SVR

Indresh Bhattacharyya

Why I Left My Big Fancy Tech Job and Wrote a Book

Jessica Powell

When Self-Help Just Makes Your Life Worse

Maggie Puniewska