The 15-Day AI/ML Interview Bootcamp
Day 11 — Convolutional networks and recurrent networks, the ideas behind them
Convolution as a sliding filter, pooling, weight sharing and why CNNs beat dense layers on images; recurrence, hidden state and LSTM gates for sequences; both implemented from scratch on tiny inputs, with the CNN and RNN questions interviewers use to check you understand the structure.
You typed "dog" into your photo app and it found the dog — in the corner of one picture, filling the frame of another, half behind a chair in a third. Nobody told it where to look. Later, you dictated a message and the app spelled "their" correctly because of a word you'd said four seconds earlier. Then in an interview someone asked, "Why does a CNN need far fewer parameters than a dense network?" — and you knew the words convolution and weight sharing, but not the number that goes with them. Today you and I build both of those machines on inputs small enough to check by hand: a convolution la…
In this lesson
Unlock the rest of The 15-Day AI/ML Interview Bootcamp
Day 11 — Convolutional networks and recurrent networks, the ideas behind them is part of the full course. One payment unlocks every lesson, every other course, and every premium article — for life.