Skip to content
ml-recall

#parameter-count

55 questions from Linear Models & Regularization, Neural Network Basics, Training Deep Networks, Convolutional Neural Networks, Recurrent Neural Networks, Attention & Transformers, Graph Neural Networks, Landmark Architectures, Transfer Learning, Tokenization, Language Modeling, Autoencoders & VAEs, LLM Fundamentals & Prompting, Fine-tuning & PEFT, PyTorch

Timed test

20 questions · 20 min · score and explanations at the end

Longer test or by difficulty: mixed test with #parameter-count

Take a test
Q 1 / 55Score 0 / 0

Question 1: Short answer

mediumAI-checkedLinear Models & Regularization

You want a general quadratic function of x∈R10\mathbf{x} \in \mathbb{R}^{10}, f(x)=b+∑iwixi+∑j≤iwijxixjf(\mathbf{x}) = b + \sum_i w_i x_i + \sum_{j \le i} w_{ij} x_i x_j, and implement it as one linear layer applied to the features xix_i and all products xixjx_i x_j with j≤ij \le i. How many trainable parameters (weights plus bias) does the model have?

an integer