Repository Issue Activity (beta)

#92 Does it make sense to cache the result of topological sort?

#113 This can't be how neurons work, can it?

#81 Another way of gradient backward backpropagation

#53 Ensure backward() is idempotent

#91 An Alternative Approach: Recursive Backpropagation Without Topological Sorting

#67 Topological sort - bug

#108 META

#106 Data type issue in "micrograd/micrograd /nn.py: class Neuron(Module)/__call__(self, x)"

#104 Exercise Solution of Micrograd Lecture

#103 “🚀 New tool: Ask questions directly from YouTube lectures + get contextual answers”

#101 microjax: like micrograd but following JAX's functional style

#96 Why topological sort is needed?

#89 Am I wrong? demo.pyinb Input[7] didn't update total_loss.data after the last learning.

#87 Interactive example

#82 seems to be an issue with return statements in _radd and _rmul inside engine.py

#3 Grad should be a Value instead of python/numpy scalar

#78 Question/Idea: Automatic Gradient Clearing

#76 radd

#77 Is `y = x * x` an edge case?

#68 backward member implementation question

#72 For addition adding incrementing grading makes sense, I can't make sense out of the incrementing it for multiplication too, potential bug?

#69 type annotation lacking/ maybe also add docstrings.

#65 Adjusting parameters by sign and magnitude of gradient

#60 Reseting the grad of weights and biases is not enough

#57 Regarding the gradient update of the __sub__ operation