AI

This post will dissect and offer a brief overview of fundamental ML concepts, and rigorously explain some key principles of deep learning. This is targeted for readers with a high level understanding of ML but lack fundamentals, or need a refresher. I will assume basic math knowledge (multivariable calculus and linear algebra). ML: Capacity, Overfitting, and Underfitting What is ML? Machine Learning (ML) is a form of applied statistics that leverage computing power to estimate functions....

Mechanism and Performance are different. The ceiling on test performance is constantly dynamic. We revise the difficulty of standardized tests every year, and the limit on how many tests one could justify as a good measure of “intelligence” is infinite. We will never know if we’ve achieved AGI if we continue down this short sighted path. There will be no “AGI test”. Rather, I believe real machine intelligence will be achieved when we’ve replicated the mechanisms behind the the inner workings of the neocortex on computers....

This list serves as a record of how I’m self-learning neuroscience and its intersections with AI. There are resources listed here that aren’t about neuroscience. However, I’ve included them because they helped broaden my understanding of biology. Timeline IPR = In Progress TBD = To be done Media Type Resource Completion Date Book A Thousand Brains: A New Theory of Intelligence 2022 Book The Selfish Gene 2023 Paper Why Neurons Have Thousands of Synapses 2023 Lecture Series HTM School 2023 Paper Tolman-Eichenbaum Machine 2023 Paper A Theory of How Columns in the Neocortex Enable Learning the Structure of the World 2023 Paper Companion paper to A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex 2023 Paper A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex 2023 Paper Locations in the Neocortex: A Theory of Sensorimotor Object Recognition Using Cortical Grid Cells 2023 Paper Grid Cell Path Integration For Movement-Based Visual Object Recognition IPR Paper A thousand brains: toward biologically constrained AI TBD Paper Going Beyond the Point Neuron: Active Dendrites and Sparse Representations for Continual Learning TBD Paper Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments TBD Paper Flexible and generalizable representations of touch TBD Book The Neuroscience of Intelligence TBD Book IQ in the Meritocracy TBD Book The Age of Insight TBD Book How to Build a Brain TBD

Overview Climatehack.ai was an international hackathon themed around fighting climate change. This post will dissect some of the thought process behind our decisions and also show methods we used to build our solution. Much credit goes to my teammates Tony Liu and Andy Cai. Background Better near-term forecasting of solar electricity generation will enable electricity grid operators around the world to do a better job of scheduling their grids. For example, the UK National Energy Grid Operator currently use a combination of solar and natural gas sources to generate power....

My first ML Project was building a tool that could alert drivers if their eyes were closed for too long. This was inspired by seeing a news article about how Amazon monitors their drivers through in-truck cameras, inspiring me to wishfully turn it into something actually useful. This post will break down the design decisions I made, and explain the tools I used in depth. It will also reflect on what I’ve learned from this experience....