Andrew Trask
Founder & Leader, OpenMined | Senior Research Scientist, Google DeepMind | Oxford PhD
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Andrew Trask. Every entry undergoes editorial source verification.
Grokking Deep Learning
Authored the seminal deep learning curriculum teaching backpropagation, matrix calculus, convolution, and recurrent architectures using only standard Python and NumPy without frameworks.
Pedagogical pure NumPy implementations lack GPU-accelerated cuDNN kernels for enterprise-scale foundation model pretraining.
PySyft: Library for Secure & Private Machine Learning
Engineered an open-source decentralized privacy framework extending PyTorch and NumPy with Federated Learning, Differential Privacy, and Multi-Party Computation (SMPC) across untrusted nodes.
Encrypted tensor computation induces substantial network latency and memory overhead compared to plain-text distributed SGD.