Important units of knowledge

What curse of dimensionality

What is law of large number

What is MLE

How do you define eigen vectors and eigen values.

Discuss the curse of dimensionality in detail ?

What is deep Metric learning ?

Deep Metric learning is a group of techniques used to measure the similarity of different data samples. The goal of metric learning is to learn a representation that maps objects into embedding space. The distance in the embedded space should preserve the objects similarity. Contrasive loss and triplet loss are two popluar loss functions.

What is contrasive loss ?

The idea of contrasive loss is to design a loss function that pulls the representations (of images for example) close together for similar images and push them apart the dissimilar images

What is datacentric AI

What is sensitivity ?

What is AUC, ROC ?

What is specificity ?

What is the intution behing MobileNets

The big idea behind mobilenets is to use the depthwise seperable convolutions to build light weight deep neural networks. https://machinethink.net/blog/googles-mobile-net-architecture-on-iphone/

What are heuristics ?

Heuristics are mental shortcuts that can facilitate problem-solving and probability judgements. These strategies are generalizations or rules of thumb, reduce cognitive load and can be effective for making immediate judgements, however, they often result in irrational or inaccurate conclusions.

What is cross validation ?

Cross validation is a method of model evaluation which splits the data in creative ways in order to obtain better estimates of “real world”