ENGR 421 • Midterm IIntroduction 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.

2299 TL

766 TL a month, 3 instalments at no extra cost

42 students took this course
20 past exam questions with solutions
50 topic lessons · 6 h 41 min
4.8 rating
Access for the whole term

Instructor

Nursena Köprücü Aslan

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

Course introduction

Introduction to Machine Learning

Machine Learning Notation Explained

Machine Learning Preliminaries

Why Supervised?

Free

Hypothesis Space & Occam's Razor

Loss Functions: Measuring Mistakes

Example: Least-Squares Linear Regression

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

Maximum Likelihood Estimation(MLE)

Bernoulli Likelihood

Free

Multinomial Likelihood and Smoothing

Bayes' Theorem

Parametric Classification

Unequal Variances → Quadratic Boundary

Gaussian Classification Boundary

Parametric & Polynomial Regression

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)

The Problem

Free

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

Free

Perceptron

Training a Perceptron

Limitation: XOR

Free

MLP Architecture & Representation View

Backpropagation

Regression

Discrimination

Should we initialize all MLP weights to zero?

Introduction to Deep Learning & Activation Functions

Free

Training Deep Networks

Regularization Techniques

Tuning Network Structure

Learning Time

Time-Delay Neural Networks (TDNN)

RNN / LSTM / GRU

Generative Adversarial Networks (GANs)

Pass Rates & Majors (Bayes; Law of Total Probability)

Free

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

Free

Naive Histogram Estimator vs. Parzen Windows (Kernel)

Kernel Smoother

Naive Density Estimator (Bandwidth effect & validity)

Why Not Regression for Classification?

From Binary to Multiclass: One-vs-All / One-vs-One with a Binary Classifier

Max-shift for SoftMax

Free

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

Free

Derivative of Softmax

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

Free

Decision Boundary and Building a Network for Binary Classification

Derivative of Squared Error

True/False Reasoning on Activation, Linear Networks, and Gradient Descent

Free

Computing Total Probability

True/False on Scaling, k-NN, Intrinsic Error and Model Complexity

Reviews

4.8

5 student reviews

Only students who have this course can review it.

Aysel Kazimli

Bought the course

Bilgisayar Mühendisliği

13 days ago

Hediye İpek

Bought the course

Elektrik-Elektronik Mühendisliği

15 days ago

Ceren Erhüner

Bought the course

Endüstri Mühendisliği

21 days ago

Devrim Paçal

Bought the course

Bilgisayar Mühendisliği

11 months ago

Defne Uzel

Bought the course

Bilgisayar Mühendisliği

12 months ago

Complete the bundle

🎓 92% of Koç Üniversitesi students study with the whole bundle.

Introduction to Machine Learning

ENGR 421 • Midterm II

Introduction to Machine Learning

4.8(5)
1966 TL2299 TL14%
Introduction to Machine Learning

ENGR 421 • Midterm I

Introduction to Machine Learning

4.8(5)
1966 TL2299 TL14%
Introduction to Machine Learning

ENGR 421 • Final

Introduction to Machine Learning

4.8(5)
1966 TL2299 TL14%
998 TL off
Total:6897 TL5899 TL

Frequently asked questions about ENGR 421 Midterm I

Frequently asked questions about Unicourse

2299 TL
42 students took this course