ENGR 421 • Midterm I • Introduction to Machine Learning
Koç Üniversitesi ENGR 421 (Introduction to Machine Learning) Midterm I sınavına hazırlık paketi.
İşlenen konular: Supervised Learning, Parametric Methods, Multivariate Methods, Linear Discrimination, Multilayer Perceptrons, Deep Learning.
766 TL a month, 3 instalments at no extra cost
Instructor

Nursena Köprücü Aslan
PhD in Computer Science
Koç Üniversitesi’nde Bilgisayar Mühendisliği okudum ve aynı zamanda Matematik alanında çift anadal yaptım. Ardından Imperial College London’da Machine Learning and Artificial Intelligence alanında yüksek lisansımı tamamladım. Şu anda University of Cambridge'te doktora çalışmalarımı sürdürüyorum.
Topics
Introduction
3 topic lessons
Introduction to Machine Learning
Machine Learning Notation Explained
Machine Learning Preliminaries
Supervised Learning
4 topic lessons
Why Supervised?
Hypothesis Space & Occam's Razor
Loss Functions: Measuring Mistakes
Example: Least-Squares Linear Regression
Probability Review
11 topic lessons
Counting and Probability
Conditional Probability and Independence
Bayes' Rule
Discrete Random Variables
Continuous Random Variables
Expected Value and Variance
Bernoulli and Binomial Distributions
Continuous Uniform Distribution
Exponential Distribution
Normal Distribution
Laplace and Logistic Distributions
Parametric Methods
4 topic lessons · 4 questions
Maximum Likelihood Estimation(MLE)
Bernoulli Likelihood
Multinomial Likelihood and Smoothing
Bayes' Theorem
Parametric Classification
Unequal Variances → Quadratic Boundary
Gaussian Classification Boundary
Parametric & Polynomial Regression
Multivariate Methods
3 topic lessons · 4 questions
Modeling Multivariate Data: Estimation, Normal Distributions, and Naive Bayes
Multivariate Classification: Linear, Quadratic, and Model Selection
Discrete Features & Multivariate Regression
Sample Mean and Covariance Matrix
Mahalanobis Distance
LDA vs QDA Classification
Naive Bayes Classification (Discrete Features)
Linear Discrimination
10 topic lessons · 2 questions
The Problem
Linear Discriminant
Two Classes/Multiple Classes/Pairwise Separation
From Discriminants to Posteriors
Gradient Descent
Gradient Descent Update
Linear Regression + MSE: Gradient Descent Step Size Effects
Logistic Discrimination: Two Classes
Logistic Discrimination: K>2 Classes
Generalizing the Linear Model
Discrimination by Regression
Learning to Rank
Multilayer Perceptrons
7 topic lessons · 1 question
Perceptron
Training a Perceptron
Limitation: XOR
MLP Architecture & Representation View
Backpropagation
Regression
Discrimination
Should we initialize all MLP weights to zero?
Deep Learning
8 topic lessons
Introduction to Deep Learning & Activation Functions
Training Deep Networks
Regularization Techniques
Tuning Network Structure
Learning Time
Time-Delay Neural Networks (TDNN)
RNN / LSTM / GRU
Generative Adversarial Networks (GANs)
Past Midterm Questions I
9 questions
Pass Rates & Majors (Bayes; Law of Total Probability)
Weighted Least Squares (Closed-Form Solution, Matrix View & Interpretation)
MLE for α (positive support, exponential tail)
Linear Discriminant with Equal Variance
MLP with Hard-Threshold Units
One Shared Network vs. Three Separate Networks
Naive Histogram Estimator vs. Parzen Windows (Kernel)
Kernel Smoother
Naive Density Estimator (Bandwidth effect & validity)
Past Midterm Questions II
11 questions
Why Not Regression for Classification?
From Binary to Multiclass: One-vs-All / One-vs-One with a Binary Classifier
Max-shift for SoftMax
Why Initialize Weights Near Zero?
Adaptive Learning Rates in Gradient Descent
When Do Direct Input Output Links Help in an MLP?
Mahalanobis vs. Euclidean: Why and When?
Regularized Least Squares
Gaussian Generative Model → Logistic Posterior
Naive Bayes Text Classification with Binary Features
Derivative of Softmax
Bonus Questions
10 questions
Model Selection Using Validation Performance and Test MSE
k-NN Decision Boundaries and the Effect of k
Mean Square Error for Linear Regression
Gradient Descent Update
k-NN Regression Prediction
Decision Boundary and Building a Network for Binary Classification
Derivative of Squared Error
True/False Reasoning on Activation, Linear Networks, and Gradient Descent
Computing Total Probability
True/False on Scaling, k-NN, Intrinsic Error and Model Complexity
Reviews
5 student reviews
Only students who have this course can review it.
Aysel Kazimli
Bought the courseBilgisayar Mühendisliği
Hediye İpek
Bought the courseElektrik-Elektronik Mühendisliği
Ceren Erhüner
Bought the courseEndüstri Mühendisliği
Devrim Paçal
Bought the courseBilgisayar Mühendisliği
Defne Uzel
Bought the courseBilgisayar Mühendisliği
Complete the bundle
🎓 92% of Koç Üniversitesi students study with the whole bundle.

ENGR 421 • Midterm II
Introduction to Machine Learning
1966 TL

ENGR 421 • Midterm I
Introduction to Machine Learning
1966 TL

ENGR 421 • Final
Introduction to Machine Learning
1966 TL