例からニューラルネットワークまでの学習パス
答えを確認できる演習付きのレッスンで、直線の当てはめから勾配降下法、ロジスティック回帰、交差検証を経て小さなニューラルネットワークまで進みます。プログラミング経験は不要です。
8 問中 0 問合格- 01
Features, targets and learning from examples
Define a prediction task, fit a small model and use it on a new input.
無料 → - 02
Training, validation, test sets and data leakage
Separate fitting from model selection and check whether related examples cross the split.
無料 → - 03
Evaluation metrics, baselines and class imbalance
Count classification errors, compare a simple baseline and choose a threshold for a stated goal.
無料 → - 04
Gradient descent: minimizing a loss step by step
Train the delivery line by repeated downhill steps and see how the learning rate decides whether training converges.
無料 → - 05
Logistic regression and classification
Turn a weighted score into a probability, train it with log loss and read its decision boundary.
Interview Prep パス → - 06
Overfitting, underfitting and regularization
Compare training and validation error as model capacity grows, then shrink the weights with a penalty.
Interview Prep パス → - 07
Cross-validation and model selection
Score each candidate on every fold, choose by the averaged error and keep the test set for one final check.
Interview Prep パス → - 08
Neural networks: neurons, layers and backpropagation
Build a two-layer network that solves XOR, compute its gradients by backpropagation and train it.
Interview Prep パス →