Spooky Sale: 10% off Premium yearly · $118.80 for the first year · until Nov 6Get it

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 MLIntuitionInvent the idea behind the formula yourselfPlaylistsYour 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
      Intuition
      67 of 88

      How far can it see?

      An image model stacks windows like the blur in “Same rule everywhere”. Layer 1 slides a window widths[0] pixels wide along a row of pixels, moving steps[0] pixels each time. Layer 2 slides a window widths[1] wide over layer 1’s outputs, moving steps[1] of them each time, and so on. Write sees(widths, steps): how many input pixels can one output of the last layer see, counting every pixel that can change it?

      one layer, a window 3 wide: each output sees 3 pixels
      input pixelslayer 1 · 3 wide, step 1sees 3 pixels
      solution.pyLoading Python
      ← Same rule everywhereMerge the most common pair →