Skip to content
DeepForgeby svx
Mixedfull-curriculumsamplermathmachine-learningbreadth

30-Day Full Curriculum

33 problems·~20h·5 stages

A month-long sampler that touches nearly every category on the platform, roughly one sitting per day. You will meet vectors, derivatives, distributions, regressions, neural nets, algorithms, graphs, and information theory in a single sweep. Ideal if you are new and want to discover which track to commit to next.

Your progress

0/33 · 0%

Path readiness 0%Easy 0% · Medium 0% · Hard 0%

Continue path · Vector Addition

What you will learn

  • Sample nearly every category with one focused sitting per day
  • Build a mental map of the whole platform
  • Finish with a synthesis week across maths, models, and evaluation

1Week 1: Mathematical Language

0/7

Start where every model starts: vectors, matrix products, cosine similarity, numerical derivatives, mean and variance, and expected value.

Stage checkpoint

0/2 to pass

A checkpoint is a short retrieval test drawn from this stage: solve 2 of 3 from memory to mark the stage complete. The stage stays open either way.

Tried this set and did not pass? Record it — the next set swaps in fresh problems from the same stage.
LabRecommended next stepLogistic Regression, From ScratchEasy

2Week 2: Data and First Models

0/6

Turn data into predictions: correlation, accuracy and MSE, linear regression, k-fold splits, and binary search as an algorithm warm-up.

Stage checkpoint

0/2 to pass

A checkpoint is a short retrieval test drawn from this stage: solve 2 of 3 from memory to mark the stage complete. The stage stays open either way.

Tried this set and did not pass? Record it — the next set swaps in fresh problems from the same stage.
LabRecommended next stepLogistic Regression, From ScratchEasy

3Week 3: Deep Learning and Optimization

0/6

Neural networks and how they train: ReLU, stable softmax, a stack simulation, an SGD update, gradient descent, and the k-means assignment step.

Stage checkpoint

0/2 to pass

A checkpoint is a short retrieval test drawn from this stage: solve 2 of 3 from memory to mark the stage complete. The stage stays open either way.

Tried this set and did not pass? Record it — the next set swaps in fresh problems from the same stage.
LabRecommended next stepXOR BoundaryHard

4Week 4: Breadth Across Modalities

0/8

Broaden and consolidate: grayscale conversion, tokenization, first differences, adjacency lists, self-information, a probability classic, a full backprop gradient, and one k-means iteration.

Stage checkpoint

0/2 to pass

A checkpoint is a short retrieval test drawn from this stage: solve 2 of 3 from memory to mark the stage complete. The stage stays open either way.

Tried this set and did not pass? Record it — the next set swaps in fresh problems from the same stage.
ProjectRecommended next stepBuild a CNN from ScratchHard

5Week 5: Synthesis

0/6

Bring it together with a transformer encoder block, TF-IDF, bootstrap confidence intervals, maximum subarray, an Adam update, and the Hessian.

Stage checkpoint

0/2 to pass

A checkpoint is a short retrieval test drawn from this stage: solve 2 of 3 from memory to mark the stage complete. The stage stays open either way.

Tried this set and did not pass? Record it — the next set swaps in fresh problems from the same stage.
LabRecommended next stepSpam FilterMedium

Capstone

Collection

Close the path with one real artifact from the catalog.

30-Day Challenge

One easy problem a day for a month continues exactly the breadth this path samples.