CIFAR-10
CIFAR-10 is a widely used dataset in machine learning for image classification, consisting of 60,000 32×32 color images in 10 different classes.
Technology & Innovation
Mila (institute)
Mila is a research institute specializing in artificial intelligence based in Montreal, Canada. It focuses on machine learning and deep learning research and collaborates with academic and industry partners worldwide.
SantaCoder
SantaCoder is an open-source large language model designed for code generation and programming assistance. It is aimed at facilitating software development through AI-driven code completion and generation.
Latent diffusion model (LDM)
A latent diffusion model (LDM) is a type of generative machine learning model that performs diffusion processes in a compressed latent space, enabling efficient and high-quality image synthesis and related tasks. By operating in a lower-dimensional representation, LDMs reduce computational costs while maintaining detailed output.
GPT-2
GPT-2 is an advanced language processing AI developed by OpenAI, known for its ability to generate human-like text based on given prompts.
UNESCO Recommendation on AI Ethics
The UNESCO Recommendation on AI Ethics is an international framework adopted to guide the ethical development and deployment of artificial intelligence technologies. It emphasizes human rights, transparency, fairness, and accountability in AI systems.
Ego4D (first-person video dataset)
Ego4D is a large-scale dataset designed for first-person video understanding, aimed at enhancing machine perception through diverse real-world scenarios.
Linformer (linear complexity) – *#398*
Linformer is a neural network architecture designed to reduce the computational complexity of the Transformer model’s self-attention mechanism from quadratic to linear with respect to the input sequence length. It achieves this by projecting the attention computation into a lower-dimensional space, enabling efficient processing of long sequences.
Particle filter
A particle filter is a recursive Bayesian filter used for estimating the state of a dynamic system from a series of noisy observations.
Neural voice cloning
Neural voice cloning is a technology that uses deep learning to replicate a person’s voice by generating synthetic speech that closely mimics the original speaker’s vocal characteristics. It enables the creation of personalized speech synthesis with relatively small amounts of audio data.