✳flâneur — a map of the web's best reading

Advancements in machine learning for machine learning – Google Research Blog

blog.research.google · 1,794 words · saved by 1 readers

Posted by Phitchaya Mangpo Phothilimthana, Staff Research Scientist, Google DeepMind, and Bryan Perozzi, Senior Staff Research Scientist, Google Research With the recent and accelerated advances in machine learning (ML), machines can understand natural language, engage in conversations, draw images, create videos and more. Modern ML models are programmed and trained using ML programming frameworks, such as TensorFlow, JAX, PyTorch, among many others. These libraries provide high-level instructions to ML practitioners, such as linear algebra operations (e.g., matrix multiplication, convolution, etc.) and neural network layers (e.g., 2D convolution layers, transformer layers). Importantly, practitioners need not worry about how to make their models run efficiently on hardware because an ML framework will automatically optimize the user's model through an underlying compiler. The efficiency of the ML workload, thus, depends on how good the compiler is. A compiler typically relies on heuri

Advancements in machine learning for machine learning Skip to main content Advancements in machine learning for machine learning December 15, 2023 Posted by Phitchaya Mangpo Phothilimthana, Staff Research Scientist, Google DeepMind, and Bryan Perozzi, Senior Staff Research Scientist, Google Research Quick links Share Copy link × With the recent and accelerated advances in machine learning (ML), machines can understand natural language , engage in conversations , draw images , create videos and more. Modern ML models are programmed and trained using ML programming frameworks, such as TensorFlow

Explore this link on the map →

related reading