These questions are guranteed to be asked in Machine Learning Engineer or ML based interviews for upto 80% of your job interviews. Make sure that you cover and know about machine learning. These questions can Ace your interviews regarding ML even if you are a fresh graduate or upto 5 years of experience.
Deep Learning Interview Questions and Answers | AI & Deep Learning Interview Questions | Edureka
Type I error is a false positive, while Type II error is a false negative. Briefly stated, Type I error means claiming something has happened when it hasn’t, while Type II error means that you claim nothing is happening when in fact something is. A clever way to think about this is to think of Type I error as telling a man he is pregnant, while Type II error means you tell a pregnant woman she isn’t carrying a baby.
Stochastic gradient descent (SGD) computes the gradient using a single sample. SGD works well (Not well, I suppose, but better than batch gradient descent) for error manifolds that have lots of local maxima/minima. In this case, the somewhat noisier gradient calculated using the reduced number of samples tends to jerk the model out of local minima into a region that hopefully is more optimal. [src]
If our model is too simple and has very few parameters then it may have high bias and low variance. On the other hand if our model has large number of parameters then it’s going to have high variance and low bias. So we need to find the right/good balance without overfitting and underfitting the data. [src]
An imbalanced dataset is one that has different proportions of target categories. For example, a dataset with medical s where we have to detect some illness will typically have many more negative samples than positive samples—say, 98% of s are without the illness and 2% of s are with the illness.
With unsupervised learning, we only have unlabeled data. The model learns a representation of the data. Unsupervised learning is frequently used to initialize the parameters of the model when we have a lot of unlabeled data and a small fraction of labeled data. We first train an unsupervised model and, after that, we use the weights of the model to train a supervised model.
LeetCode (not all companies ask Leetcode questions)
I would like to solicit corrections, criticisms, and suggestions from students and other readers. Although I have tried to eliminate errors over the multi year process of writing and revising this text, a few undoubtedly remain. In particular, some typographical infelicities will no doubt find their way into the final version. I hope you will forgive them.
Contact Amir:
Contact Shlomo:
This book is available for purchase through Amazon and other standard distribution channels. Please see the publishers web page to order the book or to obtain further details on its publication. A manuscript of the book can be found below—it has been made available for personal use only and must not be sold.
This repo aims to serve as a guide to prepare for Machine Learning (AI) engineer interviews for roles at big tech companies (in particular FAANG). It has compiled based on authors personal experience and notes from his own interview preparation in 2020, when he received offers from Facebook (ML Specialist), Google (ML Engineer), Amazon (Applied Scientist), Apple (Applied Scientist), and Roku.
The following components are the most commonly used interview modules for technical ML roles at different companies. We will go through them one by one and share how one can prepare:
