Discover published sets by community

Explore tens of thousands of sets crafted by our community.

Categories

Computer Science

Machine Learning

Activation Functions in Neural Networks

Bias-Variance Tradeoff

Computer Vision Fundamental Concepts

Cross-validation Techniques

Data Preprocessing for Machine Learning

Deep Learning Fundamentals

Data Imbalance Handling

Dimensionality Reduction Methods

Ensemble Learning Techniques

Evaluation Metrics for Classification

Feature Engineering Techniques

Generative Models

Gradient Descent Variants

Hyperparameter Tuning

Machine Learning Best Practices

Loss Functions Explained

Machine Learning Security and Privacy

Machine Learning Pipelines

Machine Learning Frameworks

Model Explainability and Interpretability

Multiclass Classification Strategies

Natural Language Processing Terminology

Model Selection Criteria

Neural Network Architectures

Performance Optimization in Machine Learning

Time Series Analysis Techniques

Reinforcement Learning Concepts

Statistical Tests for Model Comparison

Hyperparameter Tuning

Flashcards

0/15

Still learning

Number of Epochs

The number of complete passes through the training dataset. Can range from a few to many thousands, depending on the size of the dataset and the problem complexity.

Learning Rate

Controls how much to update the model in response to the estimated error each time the model weights are updated. Commonly between 0.0 and 1.0.

Activation Function

Determines the output of a neuron given an input or set of inputs. Examples include sigmoid, tanh, ReLU.

Momentum

Enhances the gradient descent learning method by taking into account the past gradients when updating the weights. Typically ranges from 0 to 1.

Max Depth of Tree

In decision tree-based models, it limits the depth of the tree. It is a form of regularization to prevent overfitting. The value is often set based on model performance.

Number of Layers

Dictates the depth of a neural network, can range from 1 to many, depending on the complexity of the function being modeled.

Batch Size

Number of samples that will be propagated through the network at one time. Common values are 32, 64, 128, etc.

Number of Neurons per Layer

Dictates the width of a neural network layer, and can range from a few to potentially thousands. Influences the representational capacity of the network.

Weight Initialization

Sets the initial values of the weights. Common strategies include zero initialization, random initialization, and Xavier/Glorot initialization.

Dropout Rate

A regularisation technique where randomly selected neurons are ignored during training. Typically ranges from 0 to 1, with 0.5 being a common value.

Ensemble Size

In ensemble methods, the number of individual models to train and combine. Common values depend on the model complexity and computational resources

Learning Rate Decay

Gradually reduces the learning rate during training in order to let the algorithm settle at the minimum. Often implemented as an exponential decay.

Early Stopping

A form of regularization where you stop training as soon as the performance on a validation set begins to degrade.

Gradient Clipping Threshold

Prevents the gradients from becoming too large, which can cause issues with numerical stability and model convergence. The threshold can be a hyperparameter to tune.

Regularization Parameter

Controls the degree of regularization applied to prevent overfitting. Common types are L1 (lasso) and L2 (ridge). Values usually range from 0 to 1.

Know

Still learning

Click to flip

Know