Канал: Ahmed Fathi

Transformers-12 Putting it all together - Part B

Transformers-12 Putting it all together - Part B

Transformers-11 Putting it all together - Part-A

Transformers-11 Putting it all together - Part-A

Transformers-10 Matrix Form Of Masked Attention

Transformers-10 Matrix Form Of Masked Attention

Transfrmers-9 : Teacher Forcing and Decoder self-attention during training

Transfrmers-9 : Teacher Forcing and Decoder self-attention during training

Transfrmers-8 : Decoder self-attention - Inference

Transfrmers-8 : Decoder self-attention - Inference

Transfrmers-7 - Matrix form of query-key-value attention

Transfrmers-7 - Matrix form of query-key-value attention

Transfrmers-6: Encoder-Encoder Self-Attention

Transfrmers-6: Encoder-Encoder Self-Attention

Transformers-5 : Multi Headed Attention

Transformers-5 : Multi Headed Attention

Transformers-2 Decoder-Encoder-Attention Part A

Transformers-2 Decoder-Encoder-Attention Part A

Transformers-3 Decoder-Encoder-Attention Part B

Transformers-3 Decoder-Encoder-Attention Part B

Transformers-4 The Query-Key-Value Attention

Transformers-4 The Query-Key-Value Attention

Transformers-1 RNN Seq2seq Recap

Transformers-1 RNN Seq2seq Recap

SQL Sessions - Part 2 SELECT FROM WHERE & Subqueries

SQL Sessions - Part 2 SELECT FROM WHERE & Subqueries

SQL - Session -1 - Part 2 - pgAdmin

SQL - Session -1 - Part 2 - pgAdmin

SQL - Session - 1 - Part - 1 - Basic Introduction

SQL - Session - 1 - Part - 1 - Basic Introduction

Udemy [English] Perspective Projection Code In glMatrix

Udemy [English] Perspective Projection Code In glMatrix

Udemy [English] Perspective Projection Matrix Derivation II

Udemy [English] Perspective Projection Matrix Derivation II

word2vec embeddings P4 - skip-gram - negative sampling of context words

word2vec embeddings P4 - skip-gram - negative sampling of context words

word2vec embeddings P2 skip-gram algorithm P2

word2vec embeddings P2 skip-gram algorithm P2

Embeddings and Word-Embeddings

Embeddings and Word-Embeddings

word2vec embeddings P5 - CBOW vs skip-gram

word2vec embeddings P5 - CBOW vs skip-gram

word2vec embeddings P1 skip-gram algorithm P1

word2vec embeddings P1 skip-gram algorithm P1

Generating Embeddings in a supervised way

Generating Embeddings in a supervised way

word2vec embeddings P3 - skip-gram - sub-sampling frequent words

word2vec embeddings P3 - skip-gram - sub-sampling frequent words

166-[ENG] SVD matlab example image compression using svd

166-[ENG] SVD matlab example image compression using svd

172 -[ENG] The Pseudo Inverse Intro and intuition III

172 -[ENG] The Pseudo Inverse Intro and intuition III

177-[ENG] Left and right inverses of a matrix

177-[ENG] Left and right inverses of a matrix

175-[ENG] More Intuition about AAplus and AplusA multiplications

175-[ENG] More Intuition about AAplus and AplusA multiplications

169-[ENG] SVD The relation between PCA and SVD

169-[ENG] SVD The relation between PCA and SVD

176-[ENG] Another Derivation for the pseudo Inverse of a matrix

176-[ENG] Another Derivation for the pseudo Inverse of a matrix

174-[ENG] The Pseudo Inverse Derivation II

174-[ENG] The Pseudo Inverse Derivation II

178 -[ENG] The pseudo inverse and infinite number of least squares solutions

178 -[ENG] The pseudo inverse and infinite number of least squares solutions

173-[ENG] The Pseudo Inverse Derivation I

173-[ENG] The Pseudo Inverse Derivation I

171-[ENG] The Pseudo Inverse Intro and intuition II

171-[ENG] The Pseudo Inverse Intro and intuition II

165-[ENG] SVD svd for data compression

165-[ENG] SVD svd for data compression

168-[ENG] SVD matlab svd and pattern extraction from data part2

168-[ENG] SVD matlab svd and pattern extraction from data part2

170-[ENG] The Pseudo Inverse Intro

170-[ENG] The Pseudo Inverse Intro

167-[ENG] SVD matlab svd and pattern extraction from data part1

167-[ENG] SVD matlab svd and pattern extraction from data part1

152-[ENG] SVD The Geometric Picture 2

152-[ENG] SVD The Geometric Picture 2

161-[ENG] SVD The nonzero eigenvalues of AtA and AAt and corresponding eigenvectors

161-[ENG] SVD The nonzero eigenvalues of AtA and AAt and corresponding eigenvectors

164-[ENG] SVD Matlab and by pen numerical example rectangular matrix part2

164-[ENG] SVD Matlab and by pen numerical example rectangular matrix part2

154 -[ENG] SVD The Diagonalization Picture

154 -[ENG] SVD The Diagonalization Picture

156-[ENG] SVD Revisiting the geomteric picture

156-[ENG] SVD Revisiting the geomteric picture

153-[ENG] SVD The Geometric Picture 3

153-[ENG] SVD The Geometric Picture 3

150-[ENG] SVD singular value decomposition - introduction

150-[ENG] SVD singular value decomposition - introduction

151-[ENG] SVD The Geometric Picture 1

151-[ENG] SVD The Geometric Picture 1

158-[ENG] SVD Generaization for square matrices

158-[ENG] SVD Generaization for square matrices

159 -[ENG] SVD svd for Rectangular matrices

159 -[ENG] SVD svd for Rectangular matrices

162-[ENG] SVD Matlab and by pen numerical example square matrix

162-[ENG] SVD Matlab and by pen numerical example square matrix

157-[ENG] SVD Singular 2d Matrices with geometric intuition

157-[ENG] SVD Singular 2d Matrices with geometric intuition

160-[ENG] SVD The calculation

160-[ENG] SVD The calculation

163-[ENG] SVD Matlab and by pen numerical example rectangular matrix part1

163-[ENG] SVD Matlab and by pen numerical example rectangular matrix part1

155-[ENG] SVD The Four Spaces Picture

155-[ENG] SVD The Four Spaces Picture

270 - [ENG] ML Estimation of multivariable gaussian distribution part2

270 - [ENG] ML Estimation of multivariable gaussian distribution part2

268- [ENG] Maximum Liklihood Estimation of single variable gaussian

268- [ENG] Maximum Liklihood Estimation of single variable gaussian

267- [ENG] Quick review of Maximum Liklihood Estimation

267- [ENG] Quick review of Maximum Liklihood Estimation

261- [ENG] The linear regression equation revisited

261- [ENG] The linear regression equation revisited

266- [ENG] derivative of matrix determinant with respect to the matrix itself

266- [ENG] derivative of matrix determinant with respect to the matrix itself

262- [ENG] derivative of matrix inverse with respect to a scalar

262- [ENG] derivative of matrix inverse with respect to a scalar

264- [ENG] derivative of matrix determinant with respect to a scalar part1

264- [ENG] derivative of matrix determinant with respect to a scalar part1

269- [ENG] ML Estimation of multivariable gaussian distribution part1

269- [ENG] ML Estimation of multivariable gaussian distribution part1

263- [ENG]derivative of yT A x with respect to A

263- [ENG]derivative of yT A x with respect to A

265- [ENG] derivative of matrix determinant with respect to a scalar part2

265- [ENG] derivative of matrix determinant with respect to a scalar part2

253 - [ENG] Product differentiation rule for matrices Intro

253 - [ENG] Product differentiation rule for matrices Intro

246 - [ENG] Quick review on Double integration

246 - [ENG] Quick review on Double integration

254 - [ENG] derivative of product of two scalar functions of matrices

254 - [ENG] derivative of product of two scalar functions of matrices

250 - [ENG] Variable substitution in double integrals III

250 - [ENG] Variable substitution in double integrals III

252 - [ENG] Solved example on The jacobian matrix and double integration

252 - [ENG] Solved example on The jacobian matrix and double integration

251 - [ENG] The jacobian matrix and double integration

251 - [ENG] The jacobian matrix and double integration

256 - [ENG] derivative of dot product of two vectors with respect to a third vector

256 - [ENG] derivative of dot product of two vectors with respect to a third vector

247 - [ENG] Another way to look at double integration

247 - [ENG] Another way to look at double integration

249 - [ENG] Variable substitution in double integrals II

249 - [ENG] Variable substitution in double integrals II

257 - [ENG] derivative of Ax with respect to x

257 - [ENG] derivative of Ax with respect to x

260 - [ENG] derivative of xT A x quadratic form

260 - [ENG] derivative of xT A x quadratic form

259 - [ENG] derivative of yT A x quadratic form

259 - [ENG] derivative of yT A x quadratic form

258 - [ENG] derivative of Ax with respect to z

258 - [ENG] derivative of Ax with respect to z

255 - [ENG] derivative of product of two matrix functions of scalars

255 - [ENG] derivative of product of two matrix functions of scalars

248 - [ENG] Variable substitution in double integrals I

248 - [ENG] Variable substitution in double integrals I

243 - [ENG] Quick review on variable substitution in 1D integrals

243 - [ENG] Quick review on variable substitution in 1D integrals

239 - [ENG] The chain rule for vector wrt vector differentiation

239 - [ENG] The chain rule for vector wrt vector differentiation

238 - [ENG] Derivative of a matrix with respect to a matrix

238 - [ENG] Derivative of a matrix with respect to a matrix

241 - [ENG] The intuition of Jacopian and integration Intro

241 - [ENG] The intuition of Jacopian and integration Intro

245 - [ENG] Deeper geomteric intuition about variable substitution in 1D integrals part 2

245 - [ENG] Deeper geomteric intuition about variable substitution in 1D integrals part 2

240 - [ENG] Chain rule and matrix tensor multiplication

240 - [ENG] Chain rule and matrix tensor multiplication

235 - [ENG] Differentiation of matrix wrt a scalar

235 - [ENG] Differentiation of matrix wrt a scalar

232 - [ENG] Differentiation of vector wrt a scalar

232 - [ENG] Differentiation of vector wrt a scalar

242 - [ENG] Quick review on the fundamental theorem of calculus

242 - [ENG] Quick review on the fundamental theorem of calculus

234 - [ENG] Differentiation of vector wrt a vector and the jacobian matrix

234 - [ENG] Differentiation of vector wrt a vector and the jacobian matrix

244 - [ENG] Deeper geomteric intuition about variable substitution in 1D integrals

244 - [ENG] Deeper geomteric intuition about variable substitution in 1D integrals

236 - [ENG] Differentiation of scalar wrt a matrix

236 - [ENG] Differentiation of scalar wrt a matrix

237 - [ENG] Derivative of a vector with respect to a matrix

237 - [ENG] Derivative of a vector with respect to a matrix

231 - [ENG] Introduction To Matrix Calculus

231 - [ENG] Introduction To Matrix Calculus

233 - [ENG] Differentiation of scalar wrt a vector

233 - [ENG] Differentiation of scalar wrt a vector

s9 pb6 k means problem

s9 pb6 k means problem

s9 pb5 image compression using kmeans

s9 pb5 image compression using kmeans

A Temporary placeholder for clustering videos

A Temporary placeholder for clustering videos

s9 pb2 kmeans

s9 pb2 kmeans

s9 pb1 kmeans

s9 pb1 kmeans

SVM s9 pb 5

SVM s9 pb 5

SVM s9 pb 4

SVM s9 pb 4

SVM s9 pb 3

SVM s9 pb 3

SVM s9 pb 2

SVM s9 pb 2

SVM Deriving the dual problem from the primal

SVM Deriving the dual problem from the primal

SVM A trivial example on mapping to higher dimensional space

SVM A trivial example on mapping to higher dimensional space

[Extra] SVM The Gaussian kernel and infinite dimensional feature space proof

[Extra] SVM The Gaussian kernel and infinite dimensional feature space proof

SVM Notes about the SVM kernel trick

SVM Notes about the SVM kernel trick

SVM The Kernel matrix positive semi-definiteness and more notes

SVM The Kernel matrix positive semi-definiteness and more notes

s9 pb 1

s9 pb 1

SVM soft margin svm Derivation of dual problem

SVM soft margin svm Derivation of dual problem

[Extra] soft svm and hinge loss

[Extra] soft svm and hinge loss

soft margin svm - Very Important Notes

soft margin svm - Very Important Notes

SVM soft margin svm Introduction

SVM soft margin svm Introduction

SVM - A trivial but very important solved example

SVM - A trivial but very important solved example

SVM primal problem - derivation

SVM primal problem - derivation

Introduction to Support Vector Machines [SVM]

Introduction to Support Vector Machines [SVM]

[Extra][SVM prerequisites] Geomteric Intuition KKT for optimization with inequality constraints

[Extra][SVM prerequisites] Geomteric Intuition KKT for optimization with inequality constraints

Lagrange Multipliers - The Dual Problem [No Proof]

Lagrange Multipliers - The Dual Problem [No Proof]

[Important] KKT conditions solved problem - geometric and analytical

[Important] KKT conditions solved problem - geometric and analytical

Lagrange Multipliers - The Primal Problem

Lagrange Multipliers - The Primal Problem

[Extra] [SVM prerequisites] convex functions - 3

[Extra] [SVM prerequisites] convex functions - 3

[Extra] [proof] KKT conditions are sufficient for convex functions and constraints

[Extra] [proof] KKT conditions are sufficient for convex functions and constraints

[Extra] [SVM prerequisites] convex functions - 1

[Extra] [SVM prerequisites] convex functions - 1

[Extra] [SVM prerequisites] convex functions - 2

[Extra] [SVM prerequisites] convex functions - 2

Assignment 1 pb 27

Assignment 1 pb 27

Assignment 1 pb 28

Assignment 1 pb 28

Assignment 1 pb 25

Assignment 1 pb 25

Some notes about means and Assignment 1 pb 26

Some notes about means and Assignment 1 pb 26

Assignment 1 pb 29 30

Assignment 1 pb 29 30

Assignment 1 pb 31

Assignment 1 pb 31

Assignment 1 pb 20 21

Assignment 1 pb 20 21

Fast Review On Amdahl's law

Fast Review On Amdahl's law

Assignment 1 pb 19

Assignment 1 pb 19

Assignment 1 pb 24

Assignment 1 pb 24

Assignment 1 pb 23

Assignment 1 pb 23

Assignment 1 pb 22

Assignment 1 pb 22

s8 pb3 d Decision Trees calculation No intuition

s8 pb3 d Decision Trees calculation No intuition

KNN and decision trees for regression - Quick overview

KNN and decision trees for regression - Quick overview

Example showing that Greedy doesn't produce optimal Decision tree

Example showing that Greedy doesn't produce optimal Decision tree

s8 - pb2 Decision Trees - Intuition only

s8 - pb2 Decision Trees - Intuition only

s8 pb4 Decision Tree - Intuition only

s8 pb4 Decision Tree - Intuition only

s8 pb3 a - b - c Decision Tree calculation - No intuition

s8 pb3 a - b - c Decision Tree calculation - No intuition

s8 pb1 Knn

s8 pb1 Knn

Decision Trees - Defining the purity function - Entropy

Decision Trees - Defining the purity function - Entropy

The Decision Tree Algorithm

The Decision Tree Algorithm

Introduction To Decision Trees - part 2

Introduction To Decision Trees - part 2

Introduction To Decision Trees Part - 1

Introduction To Decision Trees Part - 1

KNN [K nearest neighbours] part 3 complexity of knn and extra notes

KNN [K nearest neighbours] part 3 complexity of knn and extra notes

KNN [K nearest neighbors - part 1 - Introduction

KNN [K nearest neighbors - part 1 - Introduction

KNN [K nearest neighbors part 2 - Notes

KNN [K nearest neighbors part 2 - Notes

Assignment 1 pb 16 17 18

Assignment 1 pb 16 17 18

Assignment 1 pb 12

Assignment 1 pb 12

Assignment 1 pb 1 2 3 4

Assignment 1 pb 1 2 3 4

Assignment 1 pb 5 6 7

Assignment 1 pb 5 6 7

Assignment 1 pb 15

Assignment 1 pb 15

Assignment 1 pb 8 and 9

Assignment 1 pb 8 and 9

Assignment 1 pb 13 14

Assignment 1 pb 13 14

Assignment 1 pb 10 and 11

Assignment 1 pb 10 and 11

Assignment 4 pb 3 - support load_with_increment in MIPS datapath

Assignment 4 pb 3 - support load_with_increment in MIPS datapath

Assignment 4 pb 7 - Part 1

Assignment 4 pb 7 - Part 1

Assignment 4 pb 2 - support lui in MIPS datapath

Assignment 4 pb 2 - support lui in MIPS datapath

Assignment 4 pb 5 - support Jr in MIPS datapath

Assignment 4 pb 5 - support Jr in MIPS datapath

Assignment 4 pb 6 - support LWR in MIPS datapath

Assignment 4 pb 6 - support LWR in MIPS datapath

Assignment 4 pb 1 - support bne in MIPS datapath

Assignment 4 pb 1 - support bne in MIPS datapath

Assignment 4 pb 4 - support JAL in MIPS datapath

Assignment 4 pb 4 - support JAL in MIPS datapath

Assignment 4 pb 7 - Part 2

Assignment 4 pb 7 - Part 2

Logistic regression s6 pb5

Logistic regression s6 pb5

Logistic regression - fast review

Logistic regression - fast review

Logistic regression s6 pb2

Logistic regression s6 pb2

Logistic regression s6 pb4

Logistic regression s6 pb4

Logistic regression - using MLE to get weights

Logistic regression - using MLE to get weights

Logistic regression s6 pb3

Logistic regression s6 pb3

Logistic regression s6 pb1

Logistic regression s6 pb1

Non Linear Regression / Polynomial regression

Non Linear Regression / Polynomial regression

Linear Regression with regularization - compact solution

Linear Regression with regularization - compact solution

Linear Regression - Introduction

Linear Regression - Introduction

Naiive Bayes classifier - CaseStudy : Text Classification

Naiive Bayes classifier - CaseStudy : Text Classification

Midterm 2019 Q2 Solution

Midterm 2019 Q2 Solution

s5 pb4 c

s5 pb4 c

s5 pb4 b - params of full gaussian bayes vs gaussian naive bayes

s5 pb4 b - params of full gaussian bayes vs gaussian naive bayes

Midterm 2019 Q1 solution

Midterm 2019 Q1 solution

s5 pb3

s5 pb3

Naiive Bayes classifier - Laplace Smoothing

Naiive Bayes classifier - Laplace Smoothing

Midterm 2019 Q3 solution

Midterm 2019 Q3 solution

Naiive Bayes classifier - Intro

Naiive Bayes classifier - Intro

Naiive Bayes classifier - Estimating probabilities from dataset

Naiive Bayes classifier - Estimating probabilities from dataset

Naiive Bayes classifier s5 pb1

Naiive Bayes classifier s5 pb1

s5 pb4 a

s5 pb4 a

s4 - pb3 c - calculating the covariance matrix iteratively

s4 - pb3 c - calculating the covariance matrix iteratively

s4 pb3 - b calculating the points mean recursively

s4 pb3 - b calculating the points mean recursively

s4 pb2 ML estimate of Bernoulli parameter q

s4 pb2 ML estimate of Bernoulli parameter q

s4 pb4 ML estimate of the erlang distribution

s4 pb4 ML estimate of the erlang distribution

s4 pb3 - a ML estimate of multivariate gaussian - special case

s4 pb3 - a ML estimate of multivariate gaussian - special case

var (a + b) - var(a - b)

var (a + b) - var(a - b)

sample variance is a biased estimate of the true variance - proof

sample variance is a biased estimate of the true variance - proof

variance of the sample mean

variance of the sample mean

sample mean is a non-biased estimate of true mean - proof

sample mean is a non-biased estimate of true mean - proof

s4 pb1 ML estimate of gaussian variance in 1d

s4 pb1 ML estimate of gaussian variance in 1d

Biased estimate vs non-biased estimate - concept

Biased estimate vs non-biased estimate - concept

s2- pb4 part a

s2- pb4 part a

Special case 2 - Equal covariance matrices

Special case 2 - Equal covariance matrices