You can find my article describing the individual levels in detail at Towards Data Science. The list is also on GitHub.

Entry level

Data handling

• [ ] Small datasets
• [ ] Simple preprocessing
• [ ] Image data
• [ ] Audio data
• [ ] Time-series data
• [ ] Text data

Machine learning

• [ ] Regression
• [ ] Clustering
• [ ] SVMs

Networks

• [ ] Dense Neural Networks
• [ ] Convolutional Neural Networks
• [ ] Recurrent Neural Networks

Theory

• [ ] Mathematical notation
• [ ] Matrix operations
• [ ] Regression
• [ ] Clustering
• [ ] Convolution
• [ ] Simple metrics

General

• [ ] Learning the toolset
• [ ] Knowing the docs
• [ ] Data analysis
• [ ] Supervised data
• [ ] Working with metadata files
• [ ] Saving and loading models
• [ ] Callbacks

Intermediate level

Data handling

• [ ] Large datasets
• [ ] Imbalanced datasets
• [ ] Complex datasets
• [ ] Augmentations
• [ ] Normalization
• [ ] Generators
• [ ] Custom pipelines

Custom projects

• [ ] Custom image project
• [ ] Custom audio project
• [ ] Custom time-series project
• [ ] Custom text project

Networks

• [ ] Large networks
• [ ] Advanced layers
• [ ] Custom layers
• [ ] Generative networks
• [ ] Language models

Training

• [ ] Transfer learning
• [ ] Fine-tuning
• [ ] Custom embeddings
• [ ] Custom callbacks
• [ ] Data-parallel training
• [ ] Multi-GPU training
• [ ] Custom training loops
• [ ] Training in the cloud
• [ ] TPU training

Theory

• [ ] Backpropagation
• [ ] Activation functions
• [ ] Optimizers
• [ ] Losses
• [ ] Advanced metrics
• [ ] Probabilities
• [ ] Advanced layers
• [ ] Regularization
• [ ] Knowing common problems

General

• [ ] Unsupervised data
• [ ] Creating splits
• [ ] Code versioning
• [ ] Experiment tracking
• [ ] Hyperparameter search
• [ ] Model deployment
• [ ] Problem thinking
• [ ] Contributing to projects
• [ ] Reading papers

Advanced level

Data handling

• [ ] Huge datasets
• [ ] Distributed pipelines
• [ ] Multi-modal datasets

Custom projects

• [ ] Custom generative project

Training

• [ ] Mixed-precision training
• [ ] Multi-worker training
• [ ] Multi-TPU training
• [ ] Model-parallel training

Theory

• [ ] Graph neural networks
• [ ] Open-endedness
• [ ] Evolutionary algorithms
• [ ] Reinforcement learning
• [ ] Beyond computer science

General

• [ ] Efficient code
• [ ] Quantum deep learning
• [ ] Implementing papers
• [ ] Understanding papers
• [ ] Staying up-to-date
• [ ] Research