Flower: A Friendly Federated Learning Framework – Link [https://federated.withgoogle.com/] – Federated Learning – Learning better products with on-device data and privacy by default. An online comic from Google AI “The main difference between federated learning and distributed learning lies in the assumptions made on the properties of the local datasets, as distributed learning originally aims …
Application Areas[2]: Video Surveillance Event Planning and Space Design: Crowd counting can be applied in scenarios like public rallies, sports events, etc. for finding out the density of participating people. This information can be very crucial for future event planning and space design. Extended Applications: Methods used here can also be applied to counting cells …
Interpretable Machine Learning – A Guide for Making Black Box Models Explainable – Christoph Molnar – Link Interpretable AI – Building explainable machine learning systems, Ajay Thampi – Link Papers Multi-Objective Counterfactual Explanations by Susanne Dandl, Christoph Molnar, Martin Binder, Bernd Bischl – Link Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers by …
Papers/Articles Differential Privacy: The Pursuit of Protections by Default (A discussion with Miguel Guevara, Damien Desfontaines, Jim Waldo, and Terry Coatta) – November 20, 2020 Volume 18, issue 5 (ACM queue) – Link Differentially Private SQL with Bounded User Contribution by Royce J Wilson, Celia Yuxin Zhang, William Lam, Damien Desfontaines, Daniel Simmons-Marengo, and Bryant …
Papers Towards Evaluating the Robustness of Neural Networks – Nicholas Carlini, David Wagner, University of California, Berkeley – Link Defense against Universal Adversarial Perturbations – Naveed Akhtar, Jian Liu, Ajmal Mian – Link Local Gradients Smoothing: Defense against localized adversarial attacks – Muzammal Naseer, Salman H. Khan – Link Sparse and Imperceivable Adversarial Attacks – …
Boltzmann Machines Restricted Boltzmann Machines – A friendly introduction – Link Restricted Boltzmann Machines (RBMs) – Ali Ghodsi – Link Variational Auto-encoder The variational auto-encoder from Stanford CS228 Notes – Link Papers DRAW: A Recurrent Neural Network For Image Generation – Link Auxiliary Deep Generative Models – Link Generating Sentences from a Continuous Space – …
Transfer Learning vs. Domain Adaptation Following quoted from Wikipedia Domain adaptation is the ability to apply an algorithm trained in one or more “source domains” to a different (but related) “target domain”. Domain adaptation is a subcategory of transfer learning. In domain adaptation, the source and target domains all have the same feature space (but …
Manifold Hypothesis[1] Real-world high dimensional data (such as images) lie on low-dimensional manifolds embedded in the high-dimensional space. Chapter 14.6 Deep Learning Book[3] Like many other machine learning algorithms, autoencoders exploit the idea that data concentrates around a low-dimentional manifold or a small set of such manifolds. Some machine learning algorithms exploit this ideal only …
Mitesh M. Khapra Lecture PDF Introduction to Autoencoders (Video) Link between PCA and Autoencoders (Video) Regularization in autoencoders (Motivation) (Video) Denoising Autoencoders (Video) Sparse Autoencoders (Video) Contractive autoencoders (Video) Hugo Larochelle Autoencoder – definition (Video) Autoencoder – loss function (Video) Example (Video) Linear Autoencoder (Video) Autoencoder – undercomplete vs. overcomplete hidden layer (Video) Autoencoder – …
State of AI Report – 2020 by AI investors Nathan Benaich and Ian Hogarth:
