Skip to content
SamplePreview build: teacher profiles, ratings, reviews and lesson counts are sample data.
Log inFind a tutor

Teacher since July 2026

Mira Okafor

I teach how neural networks learn, one small worked example at a time

9

tutors built

4.5Sample

average from 21 reviews

424Sample

lessons taught by their tutors

About Mira

I teach the core mechanics of deep learning: what a neuron computes, how a loss turns mistakes into numbers, and how gradients and optimisers change weights. My background is in building and training models for applied research teams, which mostly meant staring at loss curves that refused to go down. That shaped how I teach. I start every idea with a tiny example you can compute by hand, then show what the same idea looks like inside a real training run. I care more about you being able to explain why something works than about you memorising formulas, and I am always clear about which explanations are settled and which are still debated.

Knows about

  • neural network fundamentals
  • activation and loss functions
  • backpropagation
  • optimisers
  • regularisation
  • initialisation and normalisation
  • training loops

Tutors by Mira

9 tutors

Backpropagation in practice

Backpropagation in practice

Follow gradients through a real network and fix the training bugs that come from misusing themIntermediateDeep learning4.5(4)91 lessonsSampleMira Okafor$7Deep learning without the jargon

Deep learning without the jargon

Understand what deep learning is, what it does well and where it fails, with no maths neededBeginnerAI basics4.7(3)78 lessonsSampleMira OkaforFreeOptimisers: SGD, momentum and Adam

Optimisers: SGD, momentum and Adam

Choose and tune optimisers and learning rate schedules with understanding instead of guessworkIntermediateDeep learning4.7(3)56 lessonsSampleMira Okafor$8Loss functions: what your model is minimising

Loss functions: what your model is minimising

Understand MSE, cross entropy and friends well enough to choose, read and debug themBeginnerDeep learning4.0(3)53 lessonsSampleMira Okafor$5Activation functions explained

Activation functions explained

Learn what ReLU, sigmoid, tanh, GELU and softmax do, and choose the right one for each layerBeginnerDeep learning4.5(2)50 lessonsSampleMira Okafor$4Overfitting, regularisation and dropout

Overfitting, regularisation and dropout

Recognise overfitting from your curves and pick the right fix, from more data to dropoutBeginnerDeep learning4.7(3)50 lessonsSampleMira Okafor$5Neurons and layers, built up by hand

Neurons and layers, built up by hand

Compute a small neural network on paper so every layer, weight and shape makes senseBeginnerDeep learning4.7(3)46 lessonsSampleMira Okafor$4Initialisation and normalisation layers

Initialisation and normalisation layers

Understand how weight initialisation and normalisation keep deep networks trainableAdvancedDeep learningNewMira Okafor$11Writing your first training loop

Writing your first training loop

Write a clear, correct training loop in any framework and know what each line is forBeginnerDeep learningNewMira Okafor$4

Recent reviews

What students said about Mira's tutors.

  • Fatima Z.Sample

    Very methodical, maybe a bit slow in the first lesson if you already know matrix multiplication. The shape tracking habit has saved me real bugs since.

    On Neurons and layers, built up by hand

  • Tomasz K.Sample

    Clear and calm. The news reading lesson was the most useful part for me. I would have liked one more example from medicine, but I understand why it stays general.

    On Deep learning without the jargon

  • Yusuf A.Sample

    Strong course. The matrix gradient part went fast and I needed to ask for a second example, which the tutor gave without fuss.

    On Backpropagation in practice

  • Liam O.Sample

    The tutor caught that I kept writing W as inputs by outputs and made me find it myself. Annoying in the moment, very useful later.

    On Neurons and layers, built up by hand

  • Arjun P.Sample

    Lesson six's checklist found my bug: I was converting an intermediate tensor to a NumPy array for logging and reusing it. Gradients stopped right there.

    On Backpropagation in practice

  • Hana K.Sample

    I liked that it kept separating backprop from the optimiser. I had been mixing them up in interviews.

    On Backpropagation in practice