Deep Learning

In this article, we will go over how to use MMDet3D in order to retrieve predictions, particularly actual coordinate values of predicted…

1. Dilated Convolution

1. Motivation

Bidrectional RNN, Deep RNN, vanishing(exploding) gradient

RNN, Forward and Back propagation, teacher forcing

Basic Structure and variance of CNN(VGG, AlexNet, ResNet, DenseNet)

Convolution, Correlation, advantages of CNN

SGD, Momentum, Adaptive Learning rate

L1, L2, Early Stopping, and Data Augmentation

Basics of the Weight Initialization and Batch Normalization

Gradient Descents, Learning Rates, ReLU, MSE, Derivative of Cross Entropy

1. Error Backpropagation