Deep learning
Neural networks from single neurons to full training loops, with worked examples.
28tutors
6teachers
2free to start
$4 to $13per paid lesson
Deep learning tutors
28 tutors
Neurons 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 sense46 lessonsSampleMira Okafor$4How language models are pretrainedHow language models are pretrained
Understand the data, objective, scaling and stability work behind large language model pretraining45 lessonsSampleMateo Rojas$13Autoencoders and latent spacesAutoencoders and latent spaces
Learn how networks compress data into a small code and rebuild it, and what that code is good for44 lessonsSampleMateo Rojas$5Data augmentation for visionData augmentation for vision
Choose image augmentations that reflect real variation, keep labels correct and improve generalisation44 lessonsSampleNoor Siddiqui$4Diffusion models from noise to sampleDiffusion models from noise to sample
Understand how diffusion models learn to remove noise and how guidance and latents shape the result44 lessonsSampleMateo Rojas$12How to read a deep learning paperHow to read a deep learning paper
Read papers in passes, find the real claim and judge the evidence behind it41 lessonsSampleNikolai Sorin$6Reinforcement learning basicsReinforcement learning basics
Understand agents, rewards and policies, and compute a Q learning update yourself41 lessonsSampleNikolai SorinFreeRNNs, LSTMs and why transformers took overRNNs, LSTMs and why transformers took over
Understand recurrent networks, their gates and limits, and the real reasons attention replaced them32 lessonsSampleNikolai Sorin$7Initialisation and normalisation layersInitialisation and normalisation layers
Understand how weight initialisation and normalisation keep deep networks trainableMira Okafor$11Positional information in transformersPositional information in transformers
Learn how transformers know word order, from sinusoids to rotary embeddings and long context limitsNikolai Sorin$8Writing your first training loopWriting your first training loop
Write a clear, correct training loop in any framework and know what each line is forMira Okafor$4Self supervised and contrastive learningSelf supervised and contrastive learning
Learn how models build useful representations from unlabelled data, and how to test themMateo Rojas$11Teachers who teach Deep learning
They wrote the lesson plans these tutors follow.
Neha Varadan
Fine tuning with judgment: when to do it, how to do it well, and how to know it workedfine tuning strategy, dataset preparation, LoRA and parameter efficient methods9 tutorsSampleMira Okafor
I teach how neural networks learn, one small worked example at a timeneural network fundamentals, activation and loss functions, backpropagation9 tutorsSampleNoor Siddiqui
Computer vision taught through real images, real failure cases and careful evaluationimage classification, object detection, segmentation9 tutorsSampleNikolai Sorin
Architectures explained from the inside: convolutions, recurrence, attention and beyondconvolutional networks, recurrent networks, transformers9 tutorsSampleMagnus Eriksen
Making models fast, small and affordable: hardware, quantisation, serving and edgeGPUs and accelerators, training cost estimation, quantisation9 tutorsSampleMateo Rojas
Generative models and representation learning, explained with intuition first and maths secondtransfer learning, autoencoders, GANs9 tutorsSampleMore in Machine learning
- Machine learning How models learn from data: training, validation, overfitting and the classic methods. 35 tutors
- Data science and statistics Clean data, explore it and draw conclusions you can defend. 30 tutors
- Math for AI The linear algebra, calculus and probability behind modern models, one idea at a time. 23 tutors
- NLP Work with text: tokens, embeddings, classification, translation and speech. 14 tutors
- Computer vision Models that see: classification, detection, segmentation and their limits. 14 tutors
- Fine tuning and training Adapt a model to your task with good data and careful training runs. 12 tutors
- MLOps and deployment Ship models to production and keep them healthy: serving, monitoring, updates. 18 tutors