LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study
This paper addresses the problem of tedious training steps in LLMs for researchers seeking more efficient and explainable models.
This paper introduces a new LLM architecture that claims to find the global optimum of the loss function in closed form, eliminating the need for deep neural network training. It is based on RBF networks but with a major twist that allows for one-iteration optimization.
The purpose of this article is to provide validation to my deep neural network alternative in the context of LLMs. Very recently, there has been a significant interest by Chinese researchers in a model called RBF network, as a substitute to standard DNNs, with increased explainability and higher accuracy. It turns out that my new model, discovered independently, is based on the exact same machinery. But with a major twist: it does not need DNN as it finds the global optimum of the loss function in closed form, in one iteration, thus eliminating the tedious training step. Here I provide a high-level overview of my technology, with case study and comparison to similar methods.