Deep-ML
Learn
Problems1,200+ hands-on ML problemsLearning PathA guided route through the fundamentalsLabsInteractive labs on real techniquesProjectsBuild a GPT, an RL agent, CUDA kernelsCollectionsCurated problem sets and videosMathPen-and-paper math for MLPlaylistsYour own problem lists, shareableStudy AssistantAn AI teacher that knows your progress
Interview Prep
Compete
ContestsFresh problem sets, ranked liveLeaderboardWhere you stand, globallyBuddiesSolve with a friend: streaks, a weekly board, chat
Discuss
Deep-Path
Premium

      Machine Learning Problem Collections

      Curated collections of machine learning problems organized by topic. Track your progress through each collection, complete all problems to earn badges, and follow structured learning sequences covering neural networks, linear algebra, optimization, and more.

      Collections
      PyTorch Basics badge

      PyTorch Basics

      The essentials of deep learning with PyTorch. Start with tensors and autograd, build up through neurons, core activation and loss functions, the standard layers (dense, dropout, batch norm, conv), optimizers, data loading, and a full training loop. Every question is written in PyTorch.

      0/28
      0%

      1. Tensor Fundamentals

      0/2
      • Create and Inspect a Tensor
      • Reshape and Transpose a Tensor

      2. Autograd & Gradients

      0/3
      • Gradient of a Square with Autograd
      • Gradient of a Weighted Sum of Squares
      • Unknown LabLab

      3. Neurons & Layers

      0/2
      • Single Linear Neuron Forward
      • Two-Layer MLP Forward Pass

      4. Activation Functions

      0/2
      • Implement ReLU and Leaky ReLU
      • Numerically Stable Softmax

      5. Loss Functions

      0/2
      • Mean Squared Error from Scratch
      • Binary Cross-Entropy from Logits

      6. Regularization & Normalization

      0/3
      • Dropout in Train vs Eval Mode
      • BatchNorm1d Forward in Eval Mode
      • MLP with Dropout and BatchNormLab

      7. Convolution

      0/3
      • Conv2d Output Shape
      • Apply a 2D Convolution
      • Unknown LabLab

      8. Optimizers

      0/4
      • One SGD Update Step
      • SGD with Momentum Step
      • One Adam Update Step
      • MNIST: Design Your Own Pytorch OptimizerLab

      9. Data Loading

      0/2
      • Batch a TensorDataset with DataLoader
      • MNIST: Pytorch DataLoaderLab

      10. Building Models

      0/2
      • Count Parameters of a Sequential Model
      • MNIST: Design-Your-Own tiny Pytorch ModelLab

      11. Training Loop

      0/3
      • One Training Step
      • PyTorch: Implement Your Own Gradient Descent Training StepLab
      • PyTorch: Build a Complete Training LoopLab