WikiText-2
WikiText-2 is a dataset designed for training language models, particularly in understanding and generating text.
Artificial Intelligence
CommonsenseQA
CommonsenseQA is a benchmark dataset designed to evaluate the ability of artificial intelligence systems to perform commonsense reasoning through multiple-choice questions. It consists of questions that require understanding and applying everyday knowledge beyond factual recall.
FeUdal networks (hierarchical RL)
FeUdal networks are a model in hierarchical reinforcement learning that enables efficient learning by structuring tasks into layers of subgoals.
DALL-E 3
DALL-E 3 is an advanced AI image generation model developed by OpenAI, designed to produce detailed and coherent images from textual descriptions. It represents a significant progression in text-to-image synthesis, improving upon its predecessors in terms of image quality and understanding of complex prompts.
Loihi (Intel)
Loihi is a neuromorphic research chip developed by Intel designed to mimic the architecture and function of the human brain for efficient artificial intelligence applications. It features spiking neural networks and event-driven computation to enable low-power learning and adaptation.
Batch normalization
Batch normalization is a technique used in deep learning to improve the training speed and stability of artificial neural networks by normalizing layer inputs. It helps reduce internal covariate shift, allowing higher learning rates and reducing the sensitivity to initialization.
Deep belief network
A deep belief network (DBN) is a generative graphical model composed of multiple layers of stochastic, latent variables. It is commonly used in machine learning for unsupervised feature learning, dimensionality reduction, and classification tasks.
Adversarial example
An adversarial example is a specially crafted input designed to deceive machine learning models, causing them to make incorrect predictions or classifications. These examples exploit vulnerabilities in models, often with minimal perturbations imperceptible to humans.
Precision and recall
Precision and recall are fundamental metrics used to evaluate the performance of classification and information retrieval systems. Precision measures the accuracy of positive predictions, while recall measures the ability to identify all relevant instances.
Charades (human activity dataset)
The Charades dataset is a large-scale dataset for human activity recognition in video, widely used for training and evaluating machine learning models.