list from [[]] and !outgoing([[]])🧾 Project Description
The idea is to create some sort of AI (likely a spiking neural network, SNN), that can be trained to do one task, then combined with another that can be trained to do another so that it can learn. Research to be done into the feasibility of this and the training time expectancy with each.
This is part of my growing interest in Explainable-AI. I want to understand machine learning, and specifically neural networks at a deeper level. I strongly feel that decoding the black box of deep learning will be one of the largest challenges of the 21st century.
🎯 Objective
The objective is to steep my toes into the realm of AI, and really learn how stuff works. I expect that this will be math heavy and I’ll really have to learn Linear Algebra and understand Eigenvectors.
📂 Project Logs
🗣️ Blurt
This is the most intense project on my plate, and I really want to get started on something in this realm. It remains to be seen how this end up. My biggest inspiration is the Churchland-Centrality-of-Factors talk that Mark Churchland gave.
Algorithm to neural network compiler?