Structured Active Recall for Complex Coursework.
Turn your lecture PDFs into flashcards, adaptive quizzes, and spaced repetition reviews in seconds.
Start Free Sprint →Supervised vs Unsupervised Learning, Linear/Logistic Regression, Decision Trees (ID3), SVM, Multi-Layer Perceptron (Backpropagation), Convolutional Neural Networks (CNN), and RNN/LSTM.
Key Points: Use chain rule: dE/dw_ij = (dE/da_j) * (da_j/dz_j) * (dz_j/dw_ij). Output layer error delta_k = (y_k - t_k) * f'(z_k). Hidden layer error delta_j = sum(delta_k * w_kj) * f'(z_j). Weight update rule: w_ij^(new) = w_ij^(old) - eta * delta_j * x_i.
Key Points: Output size formula: O = ((W - F + 2P)/S) + 1. Describe spatial feature extraction via kernels, non-linearity via ReLU, dimensional reduction / translation invariance via Max Pooling, and Softmax dense output.
Upload your Machine Learning and Deep Learning lecture slides to generate spaced repetition study cards in seconds.
Turn your lecture PDFs into flashcards, adaptive quizzes, and spaced repetition reviews in seconds.
Start Free Sprint →