Welcome to My Wiki Page

Some perspectives I have on Neuroscience, Mathematics, Machine Learning, and other areas of interest. I like to write some small articles becase (1) to share some ideas I have and (2) it gets me to think about the connections between what I learned.

Back to my website

Here are some of my notes that I will later on write them into articles: notes

---

Neuroscience Related

I think that the process of thoughts and cognition may be coming from something or a mechanism that we don't understand yet. But the faciliattion of how they go from thoughts to action is what we can seek to understood and such biological mechanistic insgights may help us to accomplish our goals in everyday life. Moreover, I also found neuroscience and biology to be quite amazing in how they may inspire the design of intelligent algorithms/systems and how "close" they may be to the true "structure" in nature that makes intelligence.

• Cognitive Neuroscience Perspectives
  Building a perspective on the brain.

• Sensory, Processing, Affective Neuroscience
  From sensory to processing to perception.

• Reinforcing & Parallel Processing
  Reinforcing & searching: some magnificent connections between the brain and algorithms.

• Neural Adaptation With Cost: Systematic Balance Distortion
  Addiction is a systematic adaptation to deviation—a well-rounded circular circuit that feeds into itself. Once balance is distorted, problems may occur.

• What We Think Determines What We Can Think
  Once the circuit forms, the rest becomes much easier.

• What You Think May Not Be What You Think
  What we feel in the moment may not be true and what we think now may not be real.

---

Mathematics Related

I find theoretical math to be pretty fun. I think that good practical techniques that work well are derived from a theoretical root.

• Twitch on Theory In Convex Optimization
  Deriving everything we want in optimization from Taylor Theory and with small modification on some assumptions or the way we design things, we get completely different families of algorithms.

• All You Need Is Constraint Solving
  All hard problems that we want to solve can be framed as a constraint solving process if we look at them from a particular perspective. Both in math and in life.

• Unfolding Stochasticity Sequentially
  Modeling interactions between stochasticity across time sequentially through the key representational example of Random Walk.

• \(N(\mu, \sigma)\) Lend It Some Confidence
  There are deep connections between statistics and probability, even on very basic statistics levels.