Fig 42. Vectorized Forward Propagation on OR gate dataset
Fig 44.c. Vectorized Backward on OR gate data
Fig 46. Vectorized Forward Propagation with updated weights and bias
Fig 48. Cost curve and Decision boundary after 5000 epochs

Fig 56. Proof that ∂Cost/∂b is the sum of upstream gradients
Fig 60. Derivation of ∂Cost/∂W after visualization.
Fig 61. Proof that ∂Cost/∂W is the dot product between the Upstream gradient and the transpose of Xₜᵣₐᵢₙ

Fig 71. Forward Propagation in the first training iteration
Fig 72. Backpropagation in the first training iteration
Fig 74. Learning Curve and Decision Boundary of the neural net with a feature cross
Fig 78. Expanded neural network with one hidden layer
Fig 84. Learning Curve and Decision boundary of the neural net with one hidden layer

Fig 93. The Learning Curve, Decision Boundary, and Shaded Decision Boundary.

Towards AI

Towards AI, is the world’s fastest-growing AI community for learning, programming, building and implementing AI.

Rafay Khan

Written by

Figuring it out. @RafayAK

Towards AI

Towards AI, is the world’s fastest-growing AI community for learning, programming, building and implementing AI.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade