InThe StartupbyArun JagotaWhy Learn Deep?Plus some how. Plus a little bit of image processingJun 23, 2019Jun 23, 2019
InTDS ArchivebyArun JagotaThe Simplest Interesting (and Useful) Recurrent Neural NetworkA recurrent neural network (RNN) processes an input sequence arriving as a stream. It maintains state, i.e. memory. This captures whatever…Nov 23, 2020Nov 23, 2020
Arun JagotaThis picture depicts the anatomy of an artificial neuron.The three most well-known activation functions — sigmoid, linear, and step — are shown. Use the linear when modeling an output that varies…Dec 5, 2020Dec 5, 2020
InTDS ArchivebyArun JagotaTwo Fundamental Neural Network Anatomical StructuresFully-connected versus ConvolutionalDec 7, 2020Dec 7, 2020
InTDS ArchivebyArun JagotaWhy ‘Learn To Forget’ in Recurrent Neural NetworksIllustrated with a simple exampleJan 2, 2021Jan 2, 2021
InTDS ArchivebyArun JagotaSequence To Sequence Labeling with Recurrent Neural NetworksThe Encoder-Decoder ModelAug 13, 2021Aug 13, 2021
