diff --git a/topics/adversarial-attacks/index.md b/topics/adversarial-attacks/index.md new file mode 100644 index 000000000000..eeccc6937c24 --- /dev/null +++ b/topics/adversarial-attacks/index.md @@ -0,0 +1,7 @@ +--- +display_name: Adversarial attacks +short_description: Adversarial attacks craft perturbed inputs to mislead machine learning models into producing incorrect outputs. +topic: adversarial-attacks +wikipedia_url: https://en.wikipedia.org/wiki/Adversarial_machine_learning +--- +Adversarial attacks are techniques that craft intentionally perturbed inputs to mislead machine learning models into producing incorrect outputs. They are central to research in AI robustness, security, and trustworthiness. diff --git a/topics/deep-learning/index.md b/topics/deep-learning/index.md index 79375c2f5f4c..bcd2db7d49dd 100644 --- a/topics/deep-learning/index.md +++ b/topics/deep-learning/index.md @@ -1,9 +1,8 @@ --- aliases: deeplearning, deep-learning-tutorial, deep-learning-algorithms, deep-learning-papers display_name: Deep learning -short_description: Deep Learning is an artificial neural network composed of many - layers. +short_description: Deep learning is a subset of machine learning that uses multi-layered neural networks to learn representations from data. topic: deep-learning wikipedia_url: https://en.wikipedia.org/wiki/Deep_learning --- -Deep learning is an AI function and a subset of machine learning, used for processing large amounts of complex data. Deep learning can automatically create algorithms based on data patterns. +Deep learning is a subset of machine learning that uses artificial neural networks with multiple layers to automatically learn hierarchical representations from data. It powers modern breakthroughs in computer vision, natural language processing, speech recognition, and generative AI. diff --git a/topics/imagenet/index.md b/topics/imagenet/index.md new file mode 100644 index 000000000000..e51d3c33a07a --- /dev/null +++ b/topics/imagenet/index.md @@ -0,0 +1,7 @@ +--- +display_name: ImageNet +short_description: ImageNet is a large-scale visual database of labeled images organized according to the WordNet hierarchy. +topic: imagenet +wikipedia_url: https://en.wikipedia.org/wiki/ImageNet +--- +ImageNet is a large-scale visual database of labeled images organized according to the WordNet hierarchy. It has been a foundational benchmark for evaluating image classification and object recognition models in computer vision. diff --git a/topics/reinforcement-learning/index.md b/topics/reinforcement-learning/index.md new file mode 100644 index 000000000000..b1d648d98583 --- /dev/null +++ b/topics/reinforcement-learning/index.md @@ -0,0 +1,7 @@ +--- +display_name: Reinforcement learning +short_description: Reinforcement learning is a machine learning paradigm where agents learn optimal behavior through environment interaction. +topic: reinforcement-learning +wikipedia_url: https://en.wikipedia.org/wiki/Reinforcement_learning +--- +Reinforcement learning is a machine learning paradigm focused on sequential decision-making, in which an autonomous agent learns optimal behavior by interacting with a dynamic environment to maximize cumulative reward signals. diff --git a/topics/representation-learning/index.md b/topics/representation-learning/index.md new file mode 100644 index 000000000000..61d46333018f --- /dev/null +++ b/topics/representation-learning/index.md @@ -0,0 +1,7 @@ +--- +display_name: Representation learning +short_description: Representation learning is a set of machine learning techniques that automatically discover meaningful features from raw data. +topic: representation-learning +wikipedia_url: https://en.wikipedia.org/wiki/Feature_learning +--- +Representation learning is a set of techniques in machine learning that automatically discover compact and meaningful features from raw data. It underpins modern advances in natural language processing, computer vision, and speech recognition. diff --git a/topics/transformer/index.md b/topics/transformer/index.md new file mode 100644 index 000000000000..c31466448feb --- /dev/null +++ b/topics/transformer/index.md @@ -0,0 +1,7 @@ +--- +display_name: Transformer +short_description: A transformer is a deep learning architecture based on self-attention mechanisms, designed to process sequential data in parallel. +topic: transformer +wikipedia_url: https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) +--- +A transformer is a deep learning architecture based on self-attention mechanisms, designed to process sequential data in parallel. Transformers are the foundation of modern large language models and are widely used in natural language processing, computer vision, and generative AI. diff --git a/topics/vae/index.md b/topics/vae/index.md new file mode 100644 index 000000000000..0fbbb9036351 --- /dev/null +++ b/topics/vae/index.md @@ -0,0 +1,8 @@ +--- +aliases: variational-autoencoder +display_name: VAE +short_description: A variational autoencoder (VAE) is a generative model that learns compact latent representations using Bayesian inference. +topic: vae +wikipedia_url: https://en.wikipedia.org/wiki/Variational_autoencoder +--- +A variational autoencoder (VAE) is a generative model that combines deep learning with Bayesian inference to learn compact latent representations of data. VAEs are widely used for image generation, anomaly detection, and data augmentation. diff --git a/topics/world-models/index.md b/topics/world-models/index.md new file mode 100644 index 000000000000..afa859bdc7fe --- /dev/null +++ b/topics/world-models/index.md @@ -0,0 +1,6 @@ +--- +display_name: World models +short_description: World models are neural networks that learn an environment's dynamics, enabling agents to simulate and plan in latent space. +topic: world-models +--- +World models are neural networks that learn an internal representation of an environment's dynamics, enabling agents to simulate and plan within a learned latent space. They are used in model-based reinforcement learning, robotics, and autonomous decision-making.