Deep Learning / Tensor and learning foundations

Deep Learning β€” Tensor and learning foundations

Shapes, nonlinearities, losses, differentiation, optimization, and generalization.

6 lessons Β· No account required

What you will learn

  • Shapes, nonlinearities, losses, differentiation, optimization, and generalization.

  1. Tensors, axes, and batches

    Read a tensor as a contract about examples, features, and operations before interpreting its numbers.

    Start learning

  2. Affine maps, nonlinearities, and representation

    Explain what extra layers can represent and why nonlinear operations change the model family.

    Start learning

  3. Outputs, logits, and stable losses

    Match the target type, output representation, and loss reduction while keeping arithmetic numerically stable.

    Start learning

  4. Chain rule and reverse accumulation

    Trace a scalar computational graph and accumulate all paths that contribute to a parameter gradient.

    Start learning

  5. Gradient descent and numerical checks

    Use a controlled quadratic to distinguish derivative correctness from step-size behavior.

    Start learning

  6. Generalization, regularization, and honest selection

    Connect network capacity and regularization to a protected evaluation process.

    Start learning
Back to course