InFrom The ScratchbySkrew EverythingDeep Learning: Deep guide for all your matrix dimensions and calculations!Vote for next post or mention what do you want to see next here:Aug 24, 20184Aug 24, 20184
InTDS ArchivebyDavid B Rosen (PhD)How To Deal With Imbalanced Classification, Without Re-balancing the DataBefore considering over-sampling your data, try simply tuning your classification decision thresholdAug 2, 20205Aug 2, 20205
InAnalytics VidhyabyKhyati MahendruHow to Deal with Imbalanced Data using SMOTEWith a Case Study in PythonJun 25, 20197Jun 25, 20197
InTDS ArchivebyDipanjan (DJ) SarkarA Comprehensive Hands-on Guide to Transfer Learning with Real-World Applications in Deep LearningDeep Learning on Steroids with the Power of Knowledge Transfer!Nov 14, 201838Nov 14, 201838
InDeeper LearningbyJaron CollisGlossary of Deep Learning: Batch NormalisationA technique for improving the performance and stability of neural networks.Jun 27, 20171Jun 27, 20171
Hyejin KimIntro to Deep Learning — weight initializationSigmoid or tanh functions are very popular activation functions used for neural network models. When training multi-layer neural networks…Sep 28, 2021Sep 28, 2021
Tyler NisonoffWeight initialization for CNNs: A Deep Dive into He InitializationToday is the first day of my sabbatical (thanks Asana!), so I tried to learn something useful!Nov 6, 20181Nov 6, 20181
InTDS ArchivebyKiprono Elijah KoechCross-Entropy Loss FunctionA loss function used in most classification problems to optimize machine learning model…Oct 2, 202023Oct 2, 202023
Michael DietzUnderstand Deep Residual Networks — a simple, modular learning framework that has redefined…Deep residual networks took the deep learning world by storm when Microsoft Research released Deep Residual Learning for Image Recognition…May 2, 20175May 2, 20175
Andre YeThe Clever Trick Behind Google’s Inception: The 1×1 ConvolutionWhat does a 1×1 conv even do?Aug 23, 20202Aug 23, 20202
InTDS ArchivebySuki LauLearning Rate Schedules and Adaptive Learning Rate Methods for Deep LearningWhen training deep neural networks, it is often useful to reduce learning rate as the training progresses. This can be done by using…Jul 29, 201710Jul 29, 201710
