pptrain
A PyTorch-native library for pre-pretraining language models on synthetic tasks
A PyTorch-native library for pre-pretraining language models on synthetic tasks
An analytical approach to neural network initialization using covariance and eigendecomposition
Evaluating sparsity and gradient-reweighted updates as a mechanism for continual learning
A highly local, self-supervised learning procedure that optimizes each neuron individually
A series of programming language projects exploring pattern matching, macro expansion, and interpreter design
Multivariate time series forecasting of photovoltaic electricity production in Germany