Edge-cloud polarization and collaboration: A comprehensive survey for ai
Influenced by the great success of deep learning via cloud computing and the rapid
development of edge chips, research in artificial intelligence (AI) has shifted to both of the …
development of edge chips, research in artificial intelligence (AI) has shifted to both of the …
Materials and devices as solutions to computational problems in machine learning
The growth of machine learning, combined with the approaching limits of conventional
digital computing, are driving a search for alternative and complementary forms of …
digital computing, are driving a search for alternative and complementary forms of …
Solving olympiad geometry without human demonstrations
Proving mathematical theorems at the olympiad level represents a notable milestone in
human-level automated reasoning,,–, owing to their reputed difficulty among the world's best …
human-level automated reasoning,,–, owing to their reputed difficulty among the world's best …
Tpu v4: An optically reconfigurable supercomputer for machine learning with hardware support for embeddings
In response to innovations in machine learning (ML) models, production workloads changed
radically and rapidly. TPU v4 is the fifth Google domain specific architecture (DSA) and its …
radically and rapidly. TPU v4 is the fifth Google domain specific architecture (DSA) and its …
Ten lessons from three generations shaped google's tpuv4i: Industrial product
Google deployed several TPU generations since 2015, teaching us lessons that changed
our views: semi-conductor technology advances unequally; compiler compatibility trumps …
our views: semi-conductor technology advances unequally; compiler compatibility trumps …
Revisiting resnets: Improved training and scaling strategies
Novel computer vision architectures monopolize the spotlight, but the impact of the model
architecture is often conflated with simultaneous changes to training methodology and …
architecture is often conflated with simultaneous changes to training methodology and …
Mixed precision algorithms in numerical linear algebra
Today's floating-point arithmetic landscape is broader than ever. While scientific computing
has traditionally used single precision and double precision floating-point arithmetics, half …
has traditionally used single precision and double precision floating-point arithmetics, half …
Griffin: Mixing gated linear recurrences with local attention for efficient language models
Recurrent neural networks (RNNs) have fast inference and scale efficiently on long
sequences, but they are difficult to train and hard to scale. We propose Hawk, an RNN with …
sequences, but they are difficult to train and hard to scale. We propose Hawk, an RNN with …
Overlap communication with dependent computation via decomposition in large deep learning models
Large deep learning models have shown great potential with state-of-the-art results in many
tasks. However, running these large models is quite challenging on an accelerator (GPU or …
tasks. However, running these large models is quite challenging on an accelerator (GPU or …
Randomness in neural network training: Characterizing the impact of tooling
The quest for determinism in machine learning has disproportionately focused on
characterizing the impact of noise introduced by algorithmic design choices. In this work, we …
characterizing the impact of noise introduced by algorithmic design choices. In this work, we …