Todays paper: VICReg (<a href='https://arxiv.org/abs/2105.04906'>https://arxiv.org/abs/2105.04906</a>) Summary of the paper VICReg prevents representation collapse using a mixture of variance, invariance and covariance when calculating the loss. It does not require negative samples and achieves great performance on downstream tasks. Highlights of discussion<ul><li>The VICReg architecture (Figure 1)</li><li>Sensitivity to hyperparameters (Table 7)</li><li>Top 5 metric usefulness</li></ul>

Todays paper: VICReg (https://arxiv.org/abs/2105.04906) Summary of the paper VICReg prevents representation collapse using a mixture of variance, invariance and covariance when calculating the loss. It does not require negative samples and achieves great performance on downstream tasks. Highlights of discussionThe VICReg architecture (Figure 1)Sensitivity to hyperparameters (Table 7)Top 5 metric usefulness

Todays paper: VICReg (<a href="https://arxiv.org/abs/2105.04906" rel="noopener noreferrer">https://arxiv.org/abs/2105.04906</a>) Summary of the paper VICReg prevents representation collapse using a mixture of variance, invariance and covariance when calculating the loss. It does not require negative samples and achieves great performance on downstream tasks. Highlights of discussion<ul><li>The VICReg architecture (Figure 1)</li><li>Sensitivity to hyperparameters (Table 7)</li><li>Top 5 metric usefulness</li></ul>

3: VICReg

A show where three machine learning enthusiasts talk about recent papers and developments in machine learning. Watch our video on YouTube https://www.youtube.com/@argmaxfm

Science

Mathematics

A show where three machine learning enthusiasts talk about recent papers and developments in machine learning. Watch our video on YouTube https://www.youtube.com/@argmaxfm

Share 3: VICReg

Sign up to save your podcasts

3: VICReg

3: VICReg