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

Neural Network Architectures

Flashcards

0/15

Still learning

Siamese Neural Network

A type of neural network architecture that contains two or more identical subnetworks. Ideal for applications where we need to find similarities or relationships, like face verification and signature recognition.

Gated Recurrent Unit (GRU)

A variant of RNNs, similar to LSTM but simpler, having gating units that control the flow of information. They are often employed in sequence modeling tasks.

Radial Basis Function Network (RBFN)

A type of neural network that uses radial basis functions as activation functions. It's well suited for function approximation and interpolation.

Long Short-Term Memory (LSTM)

An advanced RNN which has special units called memory cells to capture long-term dependencies in sequential data. Widely used in language translation and speech recognition.

Variational Autoencoder (VAE)

A type of autoencoder that generates new instances that are similar to the input data. It is used for generative tasks such as image generation and denoising.

Generative Adversarial Network (GAN)

Consists of two neural networks, the generator and the discriminator, which are trained simultaneously through adversarial processes. GANs are used for generating synthetic data, particularly realistic images.

Restricted Boltzmann Machine (RBM)

An unsupervised neural network that can learn a probability distribution over its set of inputs. RBMs are used in dimensionality reduction, classification, and collaborative filtering.

Feedforward Neural Network

A basic neural network where connections between the nodes do not form a cycle. Typically used for simple pattern recognition and classification tasks.

Convolutional Neural Network (CNN)

Specialized for processing data with a known grid-like topology, particularly useful in image and video recognition tasks.

Autoencoder

An unsupervised neural network that learn to encode the input into a lower-dimensional representation and then decode it back. Common applications include feature learning and dimensionality reduction.

Recurrent Neural Network (RNN)

Designed to recognize sequential data, using internal state (memory) to process sequences of inputs. Commonly used in language processing tasks.

Spiking Neural Network (SNN)

Mimics the operation of human brain neurons more closely by using spike-based communication. It's an emerging type of network used in neuromorphic computing and temporal pattern recognition.

Deep Belief Network (DBN)

A class of deep neural network consisting of multiple layers of graphical models called Restricted Boltzmann Machines (RBMs). DBNs can be used for dimensionality reduction, classification, regression, and feature learning.

Capsule Neural Network (CapsNet)

Uses capsules or groups of neurons to identify properties of objects in a hierarchal manner, maintaining spatial hierarchies between features. Useful for tasks that require maintaining spatial relationships, such as object segmentation.

Transformer Network

Relies on self-attention mechanisms to weight the significance of different parts of the input data without relying on sequence-aligned RNNs or CNNs. Transformative in the field of natural language processing, used in models like BERT and GPT.

Know

Still learning

Click to flip

Know