Deep Learning Interviews: Hundreds of fully solved job interview questions from a wide range of key topics in AI.

The second edition of Deep Learning Interviews (The Amazon Softcover is printed in B&W) is home to hundreds of fully-solved problems, from a wide range of key topics in AI . It is designed to both rehearse interview or exam specific topics and provide machine learning M.Sc./Ph.D. students, and those awaiting an interview a well-organized overview of the field . The problems it poses are tough enough to cut your teeth on and to dramatically improve your skills-but they’re framed within thought-provoking questions and engaging stories. That is what makes the volume so specifically valuable to students and job seekers : it provides them with the ability to speak confidently and quickly on any relevant topic, to answer technical questions clearly and correctly, and to fully understand the purpose and meaning of interview questions and answers. Those are powerful, indispensable advantages to have when walking into the interview room. The book’s contents is a large inventory of numerous topics relevant to DL job interviews and graduate level exams . That places this work at the forefront of the growing trend in science to teach a core set of practical mathematical and computational skills. It is widely accepted that the training of every computer scientist must include the fundamental theorems of ML, and AI appears in the curriculum of nearly every university. This volume is designed as an excellent reference for graduates of such programs. The book spans almost 400 pages Hundreds of fully-solved problems Problems from numerous areas of deep learning Clear diagrams and illustrations A comprehensive index Step-by-step solutions to problems Not just the answers given, but the work shown Not just the work shown, but reasoning given where appropriate This book was written for you: an aspiring data scientist with a quantitative background , facing down the gauntlet of the interview process in an increasingly competitive field. For most of you, the interview process is the most significant hurdle between you and a dream job. Even though you have the ability, the background, and the motivation to excel in your target position, you might need some guidance on how to get your foot in the door. Your curiosity will pull you through the book’s problem sets, formulas, and instructions , and as you progress, you’ll deepen your understanding of deep learning. There are intricate connections between calculus, logistic regression, entropy, and deep learning theory; work through the book, and those connections will feel intuitive. CORE SUBJECT AREAS (VOLUME-I): VOLUME-I of the book focuses on statistical perspectives and blends background fundamentals with core ideas and practical knowledge. There are dedicated chapters on: Information Theory Calculus & Algorithmic Differentiation Bayesian Deep Learning & Probabilistic Programming Logistic Regression Ensemble Learning Feature Extraction Deep Learning: expanded chapter (100+ pages) These chapters appear alongside numerous in-depth treatments of topics in Deep Learning with code examples in PyTorch, Python and C++. Author website: http://www.interviews.ai cover-amazon-print Untitled Manuscrit Copyright I Rusty Nail 1 HOW-TO USE THIS BOOK 1.1 Introduction 1.1.1 What makes this book so valuable 1.1.2 What will I learn 1.1.3 How to Work Problems 1.1.4 Types of Problems II Kindergarten 2 LOGISTIC REGRESSION 2.1 Introduction 2.2 Problems 2.2.1 General Concepts 2.2.2 Odds, Log-odds 2.2.3 The Sigmoid 2.2.4 Truly Understanding Logistic Regression 2.2.5 The Logit Function and Entropy 2.2.6 Python/PyTorch/CPP 2.3 Solutions 2.3.1 General Concepts 2.3.2 Odds, Log-odds 2.3.3 The Sigmoid 2.3.4 Truly Understanding Logistic Regression 2.3.5 The Logit Function and Entropy 2.3.6 Python, PyTorch, CPP 3 PROBABILISTIC PROGRAMMING & BAYESIAN DL 3.1 Introduction 3.2 Problems 3.2.1 Expectation and Variance 3.2.2 Conditional Probability 3.2.3 Bayes Rule 3.2.4 Maximum Likelihood Estimation 3.2.5 Fisher Information 3.2.6 Posterior & prior predictive distributions 3.2.7 Conjugate priors 3.2.8 Bayesian Deep Learning 3.3 Solutions 3.3.1 Expectation and Variance 3.3.2 Conditional Probability 3.3.3 Bayes Rule 3.3.4 Maximum Likelihood Estimation 3.3.5 Fisher Information 3.3.6 Posterior & prior predictive distributions 3.3.7 Conjugate priors 3.3.8 Bayesian Deep Learning III High School 4 INFORMATION THEORY 4.1 Introduction 4.2 Problems 4.2.1 Logarithms in Information Theory 4.2.2 Shannon's Entropy 4.2.3 Kullback-Leibler Divergence (KLD) 4.2.4 Classification and Information Gain 4.2.5 Mutual Information 4.2.6 Mechanical Statistics 4.2.7 Jensen's inequality 4.3 Solutions 4.3.1 Logarithms in Information Theory 4.3.2 Shannon's Entropy 4.3.3 Kullback-Leibler Divergence 4.3.4 Classification and Information Gain 4.3.5 Mutual Information 4.3.6 Mechanical Statistics 4.3.7 Jensen's inequality 5 DEEP LEARNING: CALCULUS, ALGORITHMIC DIFFERENTIATION 5.1 Introduction 5.2 Problems 5.2.1 AD, Gradient descent & Backpropagation 5.2.2 Numerical differentiation 5.2.3 Directed Acyclic Graphs 5.2.4 The chain rule 5.2.5 Taylor series expansion 5.2.6 Limits and continuity 5.2.7 Partial derivatives 5.2.8 Optimization 5.2.9 The Gradient descent algorithm 5.2.10 The Backpropagation algorithm 5.2.11 Feed forward neural networks 5.2.12 Activation functions, Autograd/JAX 5.2.13 Dual numbers in AD 5.2.14 Forward mode AD 5.2.15 Forward mode AD table construction 5.2.16 Symbolic differentiation 5.2.17 Simple differentiation 5.2.18 The Beta-Binomial model 5.3 Solutions 5.3.1 Algorithmic differentiation, Gradient descent 5.3.2 Numerical differentiation 5.3.3 Directed Acyclic Graphs 5.3.4 The chain rule 5.3.5 Taylor series expansion 5.3.6 Limits and continuity 5.3.7 Partial derivatives 5.3.8 Optimization 5.3.9 The Gradient descent algorithm 5.3.10 The Backpropagation algorithm 5.3.11 Feed forward neural networks 5.3.12 Activation functions, Autograd/JAX 5.3.13 Dual numbers in AD 5.3.14 Forward mode AD 5.3.15 Forward mode AD table construction 5.3.16 Symbolic differentiation 5.3.17 Simple differentiation 5.3.18 The Beta-Binomial model IV Bachelors 6 DEEP LEARNING: NN ENSEMBLES 6.1 Introduction 6.2 Problems 6.2.1 Bagging, Boosting and Stacking 6.2.2 Approaches for Combining Predictors 6.2.3 Monolithic and Heterogeneous Ensembling 6.2.4 Ensemble Learning 6.2.5 Snapshot Ensembling 6.2.6 Multi-model Ensembling 6.2.7 Learning-rate Schedules in Ensembling 6.3 Solutions 6.3.1 Bagging, Boosting and Stacking 6.3.2 Approaches for Combining Predictors 6.3.3 Monolithic and Heterogeneous Ensembling 6.3.4 Ensemble Learning 6.3.5 Snapshot Ensembling 6.3.6 Multi-model Ensembling 6.3.7 Learning-rate Schedules in Ensembling 7 DEEP LEARNING: CNN FEATURE EXTRACTION 7.1 Introduction 7.2 Problems 7.2.1 CNN as Fixed Feature Extractor 7.2.2 Fine-tuning CNNs 7.2.3 Neural style transfer, NST 7.3 Solutions 7.3.1 CNN as Fixed Feature Extractor 7.3.2 Fine-tuning CNNs 7.3.3 Neural style transfer 8 DEEP LEARNING 8.1 Introduction 8.2 Problems 8.2.1 Cross Validation 8.2.2 Convolution and correlation 8.2.3 Similarity measures 8.2.4 Perceptrons 8.2.5 Activation functions (rectification) 8.2.6 Performance Metrics 8.2.7 NN Layers, topologies, blocks 8.2.8 Training, hyperparameters 8.2.9 Optimization, Loss 8.3 Solutions 8.3.1 Cross Validation 8.3.2 Convolution and correlation 8.3.3 Similarity measures 8.3.4 Perceptrons 8.3.5 Activation functions (rectification) 8.3.6 Performance Metrics 8.3.7 NN Layers, topologies, blocks 8.3.8 Training, hyperparameters 8.3.9 Optimization, Loss V Practice Exam 9 JOB INTERVIEW MOCK EXAM 9.0.1 Rules 9.1 Problems 9.1.1 Perceptrons 9.1.2 CNN layers 9.1.3 Classification, Logistic regression 9.1.4 Information theory 9.1.5 Feature extraction 9.1.6 Bayesian deep learning VI Volume two 10 VOLUME TWO - PLAN 10.1 Introduction 10.2 AI system design 10.3 Advanced CNN topologies 10.4 1D CNN's 10.5 3D CNN's 10.6 Data augmentations 10.7 Object detection 10.8 Object segmentation 10.9 Semantic segmentation 10.10 Instance segmentation 10.11 Image classification 10.12 Image captioning 10.13 NLP 10.14 RNN 10.15 LSTM 10.16 GANs 10.17 Adversarial attacks and defences 10.18 Variational auto encoders 10.19 FCN 10.20 Seq2Seq 10.21 Monte carlo, ELBO, Re-parametrization 10.22 Text to speech 10.23 Speech to text 10.24 CRF 10.25 Quantum computing 10.26 RL