← Back to categories

Deep Learning

Neural Network Fundamentals

8 questions

Multiple Choice

ReLU Activation Behavior

Backpropagation Chain Rule

Loss Function Selection

Weight Initialization Impact

Open-Ended

Activation Functions

Backpropagation

Loss Functions

Weight Initialization

Optimization

8 questions

Multiple Choice

Batch Size Effect on Training

Adam Optimizer Components

Learning Rate Schedule Selection

Batch Normalization During Inference

Open-Ended

Gradient Descent Variants

Adam Optimizer

Learning Rate Strategies

Batch Normalization

Regularization

8 questions

Multiple Choice

Dropout Rate Selection

L1 vs L2 Regularization

Early Stopping Criterion

Data Augmentation for CNNs

Open-Ended

Early Stopping

Data Augmentation

Dropout

Weight Decay and L2 Regularization

Convolutional Neural Networks

8 questions

Multiple Choice

Convolution Output Size

Max Pooling Purpose

Transfer Learning Strategy

Receptive Field Calculation

Open-Ended

Pooling Layers

Convolution Operation

Transfer Learning

CNN Architectures

Recurrent Neural Networks

8 questions

Multiple Choice

RNN Hidden State Purpose

LSTM Gate Functions

GRU vs LSTM Comparison

Bidirectional RNN Applications

Open-Ended

RNN Fundamentals

GRU Networks

LSTM Networks

Sequence Modeling Approaches

Training Challenges

8 questions

Multiple Choice

Vanishing Gradient Symptom

Overfitting Detection

NaN Loss Debugging

Gradient Clipping Purpose

Open-Ended

Vanishing and Exploding Gradients

Diagnosing Overfitting

Hyperparameter Tuning

Debugging Neural Networks