ML INTERVIEW QUESTIONS -PART 1
IN THESE INTERVIEW PREP SERIES WE LOOK AT IMPORTANT INTERVIEW QUESTIONS ASKED IN DATA SCIENTIST /ML AND DL ROLES . IN EACH PART WE WILL DISCUSS FEW ML INTERVIEW QUESTIONS. …
THE WORD2VEC MODEL (CBOW /SKIP-GRAM)
Understanding Word embeddings ,Semantics , and Word2vec model methods like skipgram and CBOW. WHY embeddings? remember machines can only operate on numbers . approaches like Bag of words ,tfidf provide …
BATCH NORMALISATION IN NEURAL NETWORKS
HOW BATCH NORMALISATION SPEED UP TRANING, HELPS IN SCALING AND ALSO ACTS AS A REGULARIZER IN NEURAL NETWORKS We know that normalization and feature scaling help in achieving faster training …
THE MATH BEHIND SVMs , Langrangian ,kernel
In this article we discuss the important mathematical tools used in formulation of SVMs and also point out the important questions asked in interviews . SVMs are one of those …
Understanding Transformers (NLP )
In this article we will try to understand the complex “transformers” structure , there are a lot of components involved within the structure and i hope you are familiar with …
IMPLEMENTING ATTENTION MECHANISM FROM SCRATCH
how attention mechanism layer is an upgrade from one context vector seq to seq models I MEAN WHO DOESN’T CRAVE A LITTLE ATTENTION ? IT ONLY HELPS SO MUCH . …
THE PROBLEM IN SIMPLE RNN ENCODER DECODER MODELS ,BIDIRECTIONAL ENCODERS,LSTMS(BLOG)
IF YOU KNOW THE BASIC ARCHITECTURE OF AN ENCODER DECODER MODEL , YOU WILL RECOGNIZE TE PICTURE BELOW : WHERE ” C” IS THE CONTEXT VECTOR . IN SHORT THIS …
THE PROBLEM IN SIMPLE RNN ENCODER DECODER MODELS ,BIDIRECTIONAL ENCODERS,LSTMS(BLOG) Read More »
K-means failure cases for interviews
Here we discuss the failure cases of the K-means algorithm . As we know , k-means is one of the most commonly asked algorithm in interviews its advisable to know …
DEEP LEARNING-ENCODER DECODER MODELS SUMMARISED
THIS VIDEO CONTAINS A CRISP SUMMARISATION OF BASIC ENCODER DECODER MODELS USED IN MACHINE TRANSLATION , SIMILAR CONCEPTS CAN BE TRANSCEDED TO IMAGE CAPTION GENERATORS AND MORE !
TOPICS TO COVER AFTER LSTMS,GRUS ,BIDIRECTIONAL NETWORKS(VIDEO)
FOLLOWING VIDEO SUMS UP WHAT ARE THE TOPICS ONE NEEDS TO COVER AFTER HAVING A FIRM GRIP ON LSTMS, GRUS AND DIDIRECTIONAL NETWORKS . ITS RECOMMENDED THAT YOU HAVE HANDS …
TOPICS TO COVER AFTER LSTMS,GRUS ,BIDIRECTIONAL NETWORKS(VIDEO) Read More »