Aakash BindalinTechspaceDoes Batch Norm really depends on Internal Covariate Shift for its success?The popular belief is that Batch Norm reduces ICS for better training but recently MIT has published a research paper which shows that…Sep 14, 20192Sep 14, 20192
Aakash BindalinTechspaceSkip Lists: A Randomized Data Structure for search and updateWe already know that a sorted array will allow Ο(log n) time searches via the Binary Search algorithm. Unfortunately, update operations in…Sep 6, 20192Sep 6, 20192
Aakash BindalinTechspaceSwish: A self-gated Activation FunctionRecently, Google Brain has proposed a new activation function called Swish. It is showing some remarkable performance in the networks like…Aug 23, 20193Aug 23, 20193
Aakash BindalinTechspaceHow Python’s List works so dynamically and efficiently: Amortized AnalysisSuppose you want to create an array but you don’t know about its size beforehand, this could be a problem because in computer languages…Aug 16, 2019Aug 16, 2019
Aakash BindalinTechspaceBloom Filter: A Probabilistic Search Approach in Data StructuresLet’s start with discussing a ProblemAug 12, 2019Aug 12, 2019
Aakash BindalinTechspaceMeasuring just Accuracy is not enough in machine learning, A better technique is required..Why Accuracy is not enough ?Mar 24, 2019Mar 24, 2019
Aakash BindalinTechspaceSome State of the Art Optimizers in Neural NetworksWe are going to study Momentum, Nesterov Accelerated Momentum, AdaGrad, AdaDelta, RMSProp, Adam.Feb 5, 2019Feb 5, 2019
