How muhammadtahanasir/deepfoundry works
DeepFoundry is a sequential deep-learning curriculum archive: learners progress through six subject modules, from neural-network foundations to graph neural networks, using lectures and associated notebooks. The map represents each of the 18 weeks as a learning stage. The README documents the curriculum sequence and module topics; source excerpts cover only peripheral notebook utilities, so implementation-level links are not inferred.
Main entry points: Week_1_Perceptrons_and_Introduction Perceptrons · Week_2_Forward_Propagation_and_Loss Forward And Loss · Week_3_Backpropagation_and_Calculus Backpropagation · Week_4_Activation_Functions_and_Practices Activations
Components 19
Neural Foundations
- Perceptrons
Module_1 - Artificial Neural Networks/Week_1_Perceptrons_and_Introduction - Forward And Loss
Module_1 - Artificial Neural Networks/Week_2_Forward_Propagation_and_Loss - Backpropagation
Module_1 - Artificial Neural Networks/Week_3_Backpropagation_and_Calculus
Network Improvement
- Activations
Module_2 - Improving Neural Networks/Week_4_Activation_Functions_and_Practices - Regularization
Module_2 - Improving Neural Networks/Week_5_Regularization_and_Initialization - Optimization Basics
Module_2 - Improving Neural Networks/Week_6_Optimization_Foundations - Advanced Tuning
Module_2 - Improving Neural Networks/Week_7_Advanced_Optimization_and_Tuning
Vision Models
- CNN Foundations
Module_3 - Convolutional Neural Networks/Week_8_CNN_Foundations_and_Architecture - Modern CNNs
Module_3 - Convolutional Neural Networks/Week_9_Modern_CNN_Architectures - Detection And Segmentation
Module_3 - Convolutional Neural Networks/Week_10_Advanced_Vision_Detection_and_Segmentation
Sequence Models
- RNN Foundations
Module_4 - Recurrent Neural Networks/Week_11_RNN_Foundations_and_Training - Advanced RNNs
Module_4 - Recurrent Neural Networks/Week_12_Advanced_RNN_Architectures
Representation Learning
- Autoencoders
Module_5 - Unsupervised and Self-Supervised Learning/Week_13_Autoencoders - Variational Autoencoders
Module_5 - Unsupervised and Self-Supervised Learning/Week_14_Variational_Autoencoders - Generative Adversarial Networks
Module_5 - Unsupervised and Self-Supervised Learning/Week_15_Generative_Adversarial_Networks - Self-Supervised Learning
Module_5 - Unsupervised and Self-Supervised Learning/Week_16_Self_Supervised_and_Contrastive_Learning
Graph Learning
- GNN Fundamentals
Module_6 - Graph Neural Networks/Week_17_Graph_Fundamentals_and_Message_Passing - Advanced GNNs
Module_6 - Graph Neural Networks/Week_18_Advanced_GNN_Architectures_and_Applications
Other components
- Learner
Connections 18
- Learner → Perceptrons: starts learning
README.md - Perceptrons → Forward And Loss: study next
README.md - Forward And Loss → Backpropagation: study next
README.md - Backpropagation → Activations: study next
README.md - Activations → Regularization: study next
README.md - Regularization → Optimization Basics: study next
README.md - Optimization Basics → Advanced Tuning: study next
README.md - Advanced Tuning → CNN Foundations: study next
README.md - CNN Foundations → Modern CNNs: study next
README.md - Modern CNNs → Detection And Segmentation: study next
README.md - Detection And Segmentation → RNN Foundations: study next
README.md - RNN Foundations → Advanced RNNs: study next
README.md - Advanced RNNs → Autoencoders: study next
README.md - Autoencoders → Variational Autoencoders: study next
README.md - Variational Autoencoders → Generative Adversarial Networks: study next
README.md - Generative Adversarial Networks → Self-Supervised Learning: study next
README.md - Self-Supervised Learning → GNN Fundamentals: study next
README.md - GNN Fundamentals → Advanced GNNs: study next
README.md