Your proven path to success in Machine Learning Interviews – developed by FAANG engineers. Unlock ML loops at top companies with a System Design approach.

System design is an important component of any ML interview. Being able to efficiently solve open-ended machine learning problems is a key skill that can set you apart from other engineers and increase the level of seniority at which you’re hired.

This course helps you build that skill, and goes over some of the most popularly asked interview problems at big tech companies. You’ll walk step-by-step through solving these problems, focusing in particular on how to design machine learning systems rather than just answering trivia-style questions. 

Once you’re done with the course, you’ll be able to not just ace the machine learning interview at any tech company, but impress them with your ability to think about systems at a high level. If you have a machine learning or system design interview coming up, you’ll find the course tremendously valuable.

Grokking the Machine Learning Interview

# Introduction

The definition of a self-driving car is a vehicle that drives itself, with little or no human intervention. Its system uses several sensory receptors to perceive the environment. For instance, it identifies the drivable area, weather conditions, obstacles ahead and plans the next move for the vehicle accordingly.

There are different levels of autonomy in such vehicles. Tesla currently implements assisted driving, where the driving is autonomous, but someone is behind the wheel. Waymo (Google's self-driving car), in contrast, is aiming for complete autonomy under all driving conditions (no driver required). Beyond human transportation, self-driving vehicles can also be utilized as a service for various purposes, e.g., Nuro is building self-driving vehicles for local goods transportation. 

> 📝  Self-driving vehicles are perfect real-world systems for handling multi-sensory inputs that focus primarily on computer vision-based problems (e.g., object classification/ detection/ segmentation), using machine learning.


Now that you have some context, let's look at the problem statement.



# Problem statement

The interviewer has asked you to **design a self-driving car system focusing on its perception component** (*semantic image segmentation in particular*). This component will allow the vehicle to perceive its environment and make informed driving decisions. Don't worry we will describe semantic image segmentation shortly.

# Interviewer's questions 

The interviewer might ask the following questions about this problem, narrowing the scope of the question each time.

1. How would you approach a computer vision-based problem in terms of the self-driving car?

2.  How would you train a semantic image segmentation model for autonomous driving?

3.  How will the segmentation model fit in the overall autonomous driving system architecture?

4.  How would you deal with data scarcity in imaging dataset?

5. How would you best apply data augmentation on images?

6.  What are the best model architectures for image segmentation tasks?

7. Your optimized deep learning model gives a high performance on the validation set, but it fails when you take the self-driving car on the road. Why? How would you solve this issue?

> 📝 Answers\
`Q1` will be answered shortly when we talk about *subtasks*. `Q2` and `Q3` will be answered in the *architectural components* lesson. `Q4`, `Q5` and `Q7` will be answered in the *training data generation* lesson. `Q6` will be answered in the *modelling* lesson.\
\
📝 Any other similar (multi-sensory) computer vision problem asked during the interview can be solved in a similar manner to the self-driving car problem.

Let's have a quick look at some of the major software and hardware components of the self-driving vehicle system before you attempt to answer the first question. 

Let's learn how a self-driving car can "see" its surroundings using semantic image segmentation.

Introduction

Practical ML Techniques/Concepts

Search Ranking

Feed Based System

Recommendation System

Self-Driving Car: Image Segmentation

Entity Linking System

Ad Prediction System

Problem Statement

Introduction

Problem statement

Interviewer’s questions