Avalanche: an end-to-end library for continual learning
Learning continually from non-stationary data streams is a long-standing goal and a
challenging problem in machine learning. Recently, we have witnessed a renewed and fast …
challenging problem in machine learning. Recently, we have witnessed a renewed and fast …
[PDF][PDF] Accelerating the machine learning lifecycle with MLflow.
M Zaharia, A Chen, A Davidson… - IEEE Data Eng …, 2018 - people.eecs.berkeley.edu
Abstract Machine learning development creates multiple new challenges that are not
present in a traditional software development lifecycle. These include keeping track of the …
present in a traditional software development lifecycle. These include keeping track of the …
Sampling weights of deep neural networks
We introduce a probability distribution, combined with an efficient sampling algorithm, for
weights and biases of fully-connected neural networks. In a supervised learning context, no …
weights and biases of fully-connected neural networks. In a supervised learning context, no …
Noise2inverse: Self-supervised deep convolutional denoising for tomography
AA Hendriksen, DM Pelt… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Recovering a high-quality image from noisy indirect measurements is an important problem
with many applications. For such inverse problems, supervised deep convolutional neural …
with many applications. For such inverse problems, supervised deep convolutional neural …
Som-vae: Interpretable discrete representation learning on time series
High-dimensional time series are common in many domains. Since human cognition is not
optimized to work well in high-dimensional spaces, these areas could benefit from …
optimized to work well in high-dimensional spaces, these areas could benefit from …
Developments in mlflow: A system to accelerate the machine learning lifecycle
A Chen, A Chow, A Davidson, A DCunha… - Proceedings of the …, 2020 - dl.acm.org
MLflow is a popular open source platform for managing ML development, including
experiment tracking, reproducibility, and deployment. In this paper, we discuss user …
experiment tracking, reproducibility, and deployment. In this paper, we discuss user …
Management of machine learning lifecycle artifacts: A survey
M Schlegel, KU Sattler - ACM SIGMOD Record, 2023 - dl.acm.org
The explorative and iterative nature of developing and operating ML applications leads to a
variety of artifacts, such as datasets, features, models, hyperparameters, metrics, software …
variety of artifacts, such as datasets, features, models, hyperparameters, metrics, software …
imitation: Clean imitation learning implementations
imitation provides open-source implementations of imitation and reward learning algorithms
in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation …
in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation …
The role of disentanglement in generalisation
Combinatorial generalisation—the ability to understand and produce novel combinations of
familiar elements—is a core capacity of human intelligence that current AI systems struggle …
familiar elements—is a core capacity of human intelligence that current AI systems struggle …
Lost in Latent Space: Examining failures of disentangled models at combinatorial generalisation
Recent research has shown that generative models with highly disentangled
representations fail to generalise to unseen combination of generative factor values. These …
representations fail to generalise to unseen combination of generative factor values. These …