In a recent blog entry, Jack described what we have been calling The Great Convergence: several fields merging because they use ML and Deep Learning as a way to reinvent their practices and algorithms. This morning, Atlas pointed out one of his preprint :
[1604.01475] Learning A Deep $\ell_\infty$ Encoder for Hashing one more push on "great convergence"! @IgorCarron https://t.co/1H7rSWDGcE— Atlas Wang (@atlaswang) 7 avril 2016
Learning A Deep ℓ∞ Encoder for Hashing by Zhangyang Wang, Yingzhen Yang, Shiyu Chang, Qing Ling, Thomas S. Huang
We investigate theℓ∞ -constrained representation which demonstrates robustness to quantization errors, utilizing the tool of deep learning. Based on the Alternating Direction Method of Multipliers (ADMM), we formulate the original convex minimization problem as a feed-forward neural network, named \textit{Deepℓ∞ Encoder}, by introducing the novel Bounded Linear Unit (BLU) neuron and modeling the Lagrange multipliers as network biases. Such a structural prior acts as an effective network regularization, and facilitates the model initialization. We then investigate the effective use of the proposed model in the application of hashing, by coupling the proposed encoders under a supervised pairwise loss, to develop a \textit{Deep Siameseℓ∞ Network}, which can be optimized from end to end. Extensive experiments demonstrate the impressive performances of the proposed model. We also provide an in-depth analysis of its behaviors against the competitors.
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.
No comments:
Post a Comment