Blue Yonder Senior Data Scientist Interview Questions, Process, and Tips

Back propagation is a technique used in neural networks to update the weights of the network by calculating the gradient of the loss function with respect to the weights.

• Back propagation involves calculating the error at the output layer and then propagating it back through the network to update the weights using gradient descent.

• It uses the chain rule of calculus to calculate the gradient of the loss function with res...read more

Batch normalization is a technique used in machine learning to improve the training of deep neural networks by normalizing the input of each layer.

• Batch normalization normalizes the input of each layer by adjusting and scaling the activations.

• It helps in reducing internal covariate shift, which leads to faster convergence during training.

• Batch normalization also acts as a regularizer, reducing the need for other regula...read more

Transformer architecture is a type of deep learning model that uses self-attention mechanism to process sequential data.

• Utilizes self-attention mechanism to weigh the importance of different input elements

• Consists of encoder and decoder layers for processing input and generating output

• Introduced in the paper 'Attention is All You Need' by Vaswani et al. in 2017

Back propagation over time is a method used in recurrent neural networks to update weights by propagating errors backwards through time.

• Back propagation through time (BPTT) is an extension of the backpropagation algorithm for recurrent neural networks.

• It involves unfolding the network over time and calculating gradients for each time step.

• The gradients are then used to update the weights of the network to minimize the ...read more