[{"data":1,"prerenderedAt":42},["ShallowReactive",2],{"project:/projects/mytorch":3},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"tags":10,"live_url":20,"source_url":20,"image":21,"icon":22,"featured":6,"status":23,"period":24,"role":7,"about":25,"body":29,"_type":36,"_id":37,"_source":38,"_file":39,"_stem":40,"_extension":41},"/projects/mytorch","projects",false,"","MyTorch","A foundational deep learning library built from first principles in Python",[11,12,13,14,15,16,17,18,19],"Neural Networks","Deep Learning","PyTorch","Python","C++","MLPs","CNNs","RNNs","Transformers","https://github.com/baimamboukar/MyTorch","https://github.com/baimamboukar/cosmosense/blob/main/assets/images/comso.png?raw=true","pytorch","Active Development","September 2025 - Present",[26,27,28],"Built neural network library from scratch in Python and C++ replicating PyTorch functionality.","Implemented core elements: activation functions (ReLU, GeLU, Sigmoid, Tanh), linear layers, batch normalization, optimizers (Adam, AdamW, SGD), allowing a 100% complete setup of MLPs.","Implemented essential deep learning models including CNN, RNN, LSTM, GRU and Transformers, and conducted three models training, confirming understanding of deep learning architectures.",{"type":30,"children":31,"toc":32},"root",[],{"title":7,"searchDepth":33,"depth":34,"links":35},2,1,[],"markdown","content:projects:mytorch.md","content","projects/mytorch.md","projects/mytorch","md",1786626763888]