Setup Menus in Admin Panel

Course Curriculum

How to utilise Appliedaicourse
How to learn from Appliedaicourse 00:00:00
Python for Data Science Introduction
Python, Anaconda and relevant packages installations  00:00:00
Why learn Python? 00:00:00
Keywords and identifiers 00:00:00
comments, indentation and statements 00:00:00
Variables and data types in Python 00:00:00
Standard Input and Output 00:00:00
Operators 00:00:00
Control flow: if else 00:00:00
Control flow: while loop 00:00:00
Control flow: for loop 00:00:00
Control flow: break and continue 00:00:00
Python for Data Science: Data Structures
Lists 00:00:00
Tuples part 1 00:00:00
Tuples part-2 00:00:00
Sets 00:00:00
Dictionary 00:00:00
Strings 00:00:00
Python for Data Science: Functions
Introduction 00:00:00
Types of functions 00:00:00
Function arguments 00:00:00
Recursive functions 00:00:00
Lambda functions 00:00:00
Modules 00:00:00
Packages 00:00:00
File Handling 00:00:00
Exception Handling 00:00:00
Debugging Python 00:00:00
Python for Data Science: Numpy
Numpy Introduction 00:00:00
Numerical operations on Numpy 00:00:00
Python for Data Science: Matplotlib
Getting started with Matplotlib 00:00:00
Python for Data Science: Pandas
Data Frame Basics 00:00:00
Key Operations on Data Frames 00:00:00
Getting started with pandas 00:00:00
Python for Data Science: Computational Complexity
Space and Time Complexity: Find largest number in a list 00:00:00
Binary search 00:00:00
Find elements common in two lists 00:00:00
Find elements common in two lists using a Hashtable/Dict 00:00:00
Plotting for Exploratory Data Analysis (EDA)
Introduction to IRIS dataset and 2D scatter plot 00:00:00
Pair plots 00:00:00
Limitations of Pair Plots 00:00:00
Histogram and Introduction to PDF(Probability Density Function) 00:00:00
Univariate Analysis using PDF 00:00:00
CDF(Cumulative Distribution function) of Gaussian/Normal distribution 00:00:00
Mean, Variance and Standard Deviation 00:00:00
Median 00:00:00
Percentiles and Quantiles 00:00:00
IQR(Inter Quartile Range) and MAD(Median Absolute Deviation) 00:00:00
Box-plot with Whiskers 00:00:00
Violin Plots 00:00:00
Summarizing Plots, Univariate, Bivariate and Multivariate analysis 00:00:00
Multivariate Probability Density, Contour Plot 00:00:00
Assignment-1: Data Visualization with Haberman Dataset 00:00:00
Linear Algebra
Why learn it ? 00:00:00
Introduction to Vectors(2-D, 3-D, n-D) , Row Vector and Column Vector 00:00:00
Dot Product and Angle between 2 Vectors 00:00:00
Projection and Unit Vector 00:00:00
Equation of a line (2-D), Plane(3-D) and Hyperplane (n-D), Plane Passing through origin, Normal to a Plane 00:00:00
Distance of a point from a Plane/Hyperplane, Half-Spaces 00:00:00
Equation of a Circle (2-D), Sphere (3-D) and Hypersphere (n-D) 00:00:00
Equation of an Ellipse (2-D), Ellipsoid (3-D) and Hyperellipsoid (n-D) 00:00:00
Square ,Rectangle 00:00:00
Hyper Cube,Hyper Cuboid 00:00:00
Probability and Statistics
Introduction to Probability and Statistics 00:00:00
Population and Sample 00:00:00
Gaussian/Normal Distribution and its PDF(Probability Density Function) 00:00:00
CDF(Cumulative Distribution function) of Gaussian/Normal distribution 00:00:00
Symmetric distribution, Skewness and Kurtosis 00:00:00
Standard normal variate (Z) and standardization 00:00:00
Kernel density estimation 00:00:00
Sampling distribution & Central Limit theorem 00:00:00
Q-Q plot:How to test if a random variable is normally distributed or not? 00:00:00
How distributions are used? 00:00:00
Chebyshev’s inequality 00:00:00
Discrete and Continuous Uniform distributions 00:00:00
How to randomly sample data points (Uniform Distribution) 00:00:00
Bernoulli and Binomial Distribution 00:00:00
Log Normal Distribution 00:00:00
Power law distribution 00:00:00
Box cox transform 00:00:00
Applications of non-gaussian distributions? 00:00:00
Co-variance 00:00:00
Pearson Correlation Coefficient 00:00:00
Spearman Rank Correlation Coefficient 00:00:00
Correlation vs Causation 00:00:00
How to use correlations? 00:00:00
Confidence interval (C.I) Introduction 00:00:00
Computing confidence interval given the underlying distribution 00:00:00
C.I for mean of a random variable 00:00:00
Confidence interval using bootstrapping 00:00:00
Hypothesis testing methodology, Null-hypothesis, p-value 00:00:00
Hypothesis Testing Intution with coin toss example 00:00:00
Resampling and permutation test 00:00:00
K-S Test for similarity of two distributions 00:00:00
Code Snippet K-S Test 00:00:00
Hypothesis testing: another example 00:00:00
Resampling and Permutation test: another example 00:00:00
How to use hypothesis testing? 00:00:00
Dimensionality reduction and Visualization
What is Dimensionality reduction? 00:00:00
Row Vector and Column Vector 00:00:00
How to represent a data set? 00:00:00
How to represent a dataset as a Matrix. 00:00:00
Data Preprocessing: Feature Normalisation 00:00:00
Mean of a data matrix 00:00:00
Data Preprocessing: Column Standardization 00:00:00
Co-variance of a Data Matrix 00:00:00
MNIST dataset (784 dimensional) 00:00:00
Code to Load MNIST Data Set 00:00:00
PCA (Principal Component Analysis)
Why learn PCA? 00:00:00
Geometric intuition of PCA 00:00:00
Mathematical objective function of PCA 00:00:00
Alternative formulation of PCA: Distance minimization 00:00:00
Eigen values and Eigen vectors (PCA): Dimensionality reduction 00:00:00
PCA for Dimensionality Reduction and Visualization 00:00:00
Visualize MNIST dataset 00:00:00
Limitations of PCA 00:00:00
PCA Code example 00:00:00
PCA for dimensionality reduction (not-visualization) 00:00:00
(t-SNE)T-distributed Stochastic Neighbourhood Embedding
What is t-SNE? 00:00:00
Neighborhood of a point, Embedding 00:00:00
Geometric intuition of t-SNE 00:00:00
Crowding Problem 00:00:00
How to apply t-SNE and interpret its output 00:00:00
t-SNE on MNIST 00:00:00
Code example of t-SNE 00:00:00
Real world problem: Predict rating given product reviews on Amazon
Data Cleaning: Deduplication 00:00:00
Why convert text to a vector? 00:00:00
Bag of Words (BoW) 00:00:00
Text Preprocessing: Stemming, Stop-word removal, Tokenization, Lemmatization. 00:00:00
uni-gram, bi-gram, n-grams. 00:00:00
tf-idf (term frequency- inverse document frequency) 00:00:00
Why use log in IDF? 00:00:00
Word2Vec. 00:00:00
Avg-Word2Vec, tf-idf weighted Word2Vec 00:00:00
Bag of Words( Code Sample) 00:00:00
Text Preprocessing( Code Sample) 00:00:00
Bi-Grams and n-grams (Code Sample) 00:00:00
TF-IDF (Code Sample) 00:00:00
Avg-Word2Vec and TFIDF-Word2Vec (Code Sample) 00:00:00
Avg-Word2Vec and TFIDF-Word2Vec (Code Sample) 00:00:00
Classification and Regression Models: K-Nearest Neighbors
How “Classification” works? 00:00:00
Data matrix notation 00:00:00
Classification vs Regression (examples) 00:00:00
K-Nearest Neighbours Geometric intuition with a toy example 00:00:00
Failure cases of KNN 00:00:00
Distance measures: Euclidean(L2) , Manhattan(L1), Minkowski, Hamming 00:00:00
Cosine Distance & Cosine Similarity 00:00:00
How to measure the effectiveness of k-NN? 00:00:00
Test/Evaluation time and space complexity 00:00:00
KNN Limitations 00:00:00
Decision surface for K-NN as K changes 00:00:00
Overfitting and Underfitting 00:00:00
Need for Cross validation 00:00:00
K-fold cross validation 00:00:00
Visualizing train, validation and test datasets 00:00:00
How to determine overfitting and underfitting? 00:00:00
Time based splitting 00:00:00
k-NN for regression 00:00:00
Weighted k-NN 00:00:00
Voronoi diagram 00:00:00
Binary search tree 00:00:00
How to build a kd-tree 00:00:00
Find nearest neighbours using kd-tree 00:00:00
Limitations of Kd tree 00:00:00
Extensions. 00:00:00
Hashing vs LSH 00:00:00
LSH for cosine similarity 00:00:00
LSH for euclidean distance 00:00:00
Probabilistic class label 00:00:00
Code Sample:Decision boundary . 00:00:00
Code Sample:Cross Validation 00:00:00
Classification Algorithms in Various Situations
Introduction 00:00:00
Imbalanced vs balanced dataset 00:00:00
Multi-class classification 00:00:00
k-NN, given a distance or similarity matrix 00:00:00
Train and test set differences 00:00:00
Impact of outliers 00:00:00
Local outlier Factor (Simple solution :Mean distance to Knn) 00:00:00
k distance 00:00:00
Reachability-Distance(A,B) 00:00:00
Local reachability-density(A) 00:00:00
Local outlier Factor(A) 00:00:00
Impact of Scale & Column standardization 00:00:00
Interpretability 00:00:00
Feature Importance and Forward Feature selection 00:00:00
Handling categorical and numerical features 00:00:00
Handling missing values by imputation 00:00:00
curse of dimensionality 00:00:00
Bias-Variance tradeoff. 00:00:00
Intuitive understanding of bias-variance. 00:00:00
best and worst case of algorithm 00:00:00
Performance Measurement of Models
Confusion matrix, TPR, FPR, FNR, TNR 00:00:00
Precision and recall, F1-score 00:00:00
Receiver Operating Characteristic Curve (ROC) curve and AUC 00:00:00
Log-loss 00:00:00
R-Squared/Coefficient of determination 00:00:00
Median absolute deviation (MAD) 00:00:00
Distribution of errors 00:00:00
Naive Bayes
Conditional probability 00:00:00
Independent vs Mutually exclusive events 00:00:00
Bayes Theorem with examples 00:00:00
Naive Bayes algorithm 00:00:00
Toy example: Train and test stages 00:00:00
Naive Bayes on Text data 00:00:00
Laplace/Additive Smoothing 00:00:00
Log-probabilities for numerical stability 00:00:00
Bias and Variance tradeoff 00:00:00
Feature importance and interpretability 00:00:00
Imbalanced data 00:00:00
Outliers 00:00:00
Missing values 00:00:00
Handling Numerical features (Gaussian NB) 00:00:00
Multiclass classification 00:00:00
Similarity or Distance matrix 00:00:00
Large dimensionality 00:00:00
Best and worst cases 00:00:00
Code example 00:00:00
Logistic Regression
Geometric intuition of Logistic Regression 00:00:00
Sigmoid function: Squashing 00:00:00
Mathematical formulation of Objective function 00:00:00
Weight vector 00:00:00
L2 Regularization: Overfitting and Underfitting 00:00:00
L1 regularization and sparsity 00:00:00
Probabilistic Interpretation: Gaussian Naive Bayes 00:00:00
Loss minimization interpretation 00:00:00
hyperparameter Search: Grid search and random search 00:00:00
Column Standardization 00:00:00
Feature importance and Model interpretability 00:00:00
Collinearity of features 00:00:00
Train & Run time space & time complexity 00:00:00
Real world Cases 00:00:00
Non-linearly separable data & feature engineering 00:00:00
Code sample: Logistic regression, GridSearchCV, RandomSearchCV 00:00:00
Extensions to Logistic Regression: Generalized linear models(GLM) 00:00:00
Linear Regression
Geometric intuition of Linear Regression 00:00:00
Mathematical formulation 00:00:00
Real world cases 00:00:00
Code sample for Linear Regression 00:00:00
Solving Optimization Problems
Differentiation 00:00:00
Online differentiation tools 00:00:00
Maxima and Minima 00:00:00
Vector calculus: Grad 00:00:00
Gradient descent: geometric intuition 00:00:00
Learning rate 00:00:00
Gradient descent for linear regression 00:00:00
SGD algorithm 00:00:00
Constrained Optimization & PCA 00:00:00
Logistic regression formulation revisited 00:00:00
Why L1 regularization creates sparsity? 00:00:00
Support Vector Machines (SVM)
Geometric Intution 00:00:00
Mathematical derivation 00:00:00
Why we take values +1 and and -1 for Support vector planes 00:00:00
Loss function (Hinge Loss) based interpretation 00:00:00
Dual form of SVM formulation 00:00:00
kernel trick 00:00:00
Polynomial Kernel 00:00:00
RBF-Kernel 00:00:00
Domain specific Kernels 00:00:00
Train and run time complexities 00:00:00
nu-SVM: control errors and support vectors 00:00:00
SVM Regression 00:00:00
Cases 00:00:00
Code sample 00:00:00
Decision Trees
Geometric Intuition of decision tree: Axis parallel hyperplanes 00:00:00
Sample Decision tree 00:00:00
Building a decision Tree:Entropy 00:00:00
Building a decision Tree:Information Gain 00:00:00
Building a decision Tree: Gini Impurity 00:00:00
Building a decision Tree: Constructing a DT 00:00:00
Building a decision Tree: Splitting numerical features 00:00:00
Feature standardization 00:00:00
Building a decision Tree:Categorical features with many possible values 00:00:00
Overfitting and Underfitting 00:00:00
Train and Run time complexity 00:00:00
Regression using Decision Trees 00:00:00
Cases 00:00:00
Code Samples 00:00:00
Ensemble Models
What are ensembles? 00:00:00
Bootstrapped Aggregation (Bagging) Intuition 00:00:00
Random Forest and their construction 00:00:00
Bias-Variance tradeoff 00:00:00
Train and Run time complexity 00:00:00
Bagging:Code Sample 00:00:00
Extremely randomized trees 00:00:00
Random Forest :Cases 00:00:00
Boosting Intuition 00:00:00
Residuals, Loss functions and gradients 00:00:00
Gradient Boosting 00:00:00
Regularization by Shrinkage 00:00:00
Train and Run time complexity 00:00:00
XGBoost: Boosting + Randomization 00:00:00
AdaBoost: geometric intuition 00:00:00
Stacking models 00:00:00
Cascading classifiers 00:00:00
Kaggle competitions vs Real world 00:00:00
Featurization and Feature Engineering
Kaggle Winners solutions 00:00:00
Introduction 00:00:00
Moving window for Time Series Data 00:00:00
Fourier decomposition 00:00:00
Deep learning features: LSTM 00:00:00
Image histogram 00:00:00
Keypoints: SIFT. 00:00:00
Deep learning features: CNN 00:00:00
Relational data 00:00:00
Graph data 00:00:00
Indicator variables 00:00:00
Feature binning 00:00:00
Interaction variables 00:00:00
Mathematical transforms 00:00:00
Model specific featurizations 00:00:00
Feature orthogonality 00:00:00
Domain specific featurizations 00:00:00
Feature slicing 00:00:00
Miscellaneous Topics
VC dimension 00:00:00
Calibration of Models:Need for calibration 00:00:00
Calibration Plots. 00:00:00
Platt’s Calibration/Scaling. 00:00:00
Isotonic Regression 00:00:00
Code samples. 00:00:00
Modeling in the presence of outliers: RANSAC 00:00:00
Productionizing models 00:00:00
Retraining models periodically. 00:00:00
A/B testing. 00:00:00
Data Science Life cycle 00:00:00
Case Study 1: Quora Question Pair Similarity Problem
Business/Real world problem:Problem definition 00:00:00
Business objectives and constraints. 00:00:00
Mapping to an ML problem : Data overview 00:00:00
Mapping to an ML problem : ML problem and performance metric. 00:00:00
Mapping to an ML problem : Train-test split 00:00:00
EDA: Basic Statistics. 00:00:00
EDA: Basic Feature Extraction 00:00:00
EDA: Text Preprocessing 00:00:00
EDA: Advanced Feature Extraction 00:00:00
EDA: Feature analysis. 00:00:00
EDA: Data Visualization: T-SNE. 00:00:00
EDA: TF-IDF weighted Word2Vec featurization. 00:00:00
ML Models :Loading Data 00:00:00
ML Models: Random Model 00:00:00
ML Models : Logistic Regression and Linear SVM 00:00:00
ML Models : XGBoost 00:00:00
Case Study 2: Personalized Cancer Diagnosis
Business/Real world problem Overview 00:00:00
Business objectives and constraints. 00:00:00
ML problem formulation :Data 00:00:00
ML problem formulation: Mapping real world to ML problem. 00:00:00
ML problem formulation :Train, CV and Test data construction 00:00:00
Exploratory Data Analysis:Reading data & preprocessing 00:00:00
Exploratory Data Analysis:Distribution of Class-labels 00:00:00
Exploratory Data Analysis: “Random” Model 00:00:00
Univariate Analysis:Gene feature 00:00:00
Univariate Analysis:Variation Feature 00:00:00
Univariate Analysis:Text feature 00:00:00
Machine Learning Models:Data preparation 00:00:00
Baseline Model: Naive Bayes 00:00:00
K-Nearest Neighbors Classification 00:00:00
Logistic Regression with class balancing 00:00:00
Logistic Regression without class balancing 00:00:00
Linear-SVM. 00:00:00
Random-Forest with one-hot encoded features 00:00:00
Random-Forest with response-coded features 00:00:00
Stacking Classifier 00:00:00
Majority Voting classifier 00:00:00
Case study 4:Taxi demand prediction in New York City
Business/Real world problem Overview 00:00:00
Objectives and constraints 00:00:00
Mapping to ML problem :Data 00:00:00
Mapping to ML problem :dask dataframes 00:00:00
Mapping to ML problem :Fields/Features. 00:00:00
Mapping to ML problem :Time series forecasting/Regression 00:00:00
Mapping to ML problem :Performance metrics 00:00:00
Data Cleaning :Latitude and Longitude data 00:00:00
Data Cleaning :Trip Duration. 00:00:00
Data Cleaning :Speed. 00:00:00
Data Cleaning :Distance. 00:00:00
Data Cleaning :Fare 00:00:00
Data Cleaning :Remove all outliers/erroneous points 00:00:00
Data Preparation:Clustering/Segmentation 00:00:00
Data Preparation:Time binning 00:00:00
Data Preparation:Smoothing time-series data. 00:00:00
Data Preparation:Smoothing time-series data cont.. 00:00:00
Data Preparation: Time series and Fourier transforms. 00:00:00
Ratios and previous-time-bin values 00:00:00
Simple moving average 00:00:00
Weighted Moving average. 00:00:00
Exponential weighted moving average 00:00:00
Results. 00:00:00
Regression models :Train-Test split & Features 00:00:00
Linear regression. 00:00:00
Random Forest regression 00:00:00
Xgboost Regression 00:00:00
Model comparison 00:00:00
Case study 5: Stackoverflow tag predictor
Business/Real world problem 00:00:00
Business objectives and constraints 00:00:00
Mapping to an ML problem: Data overview 00:00:00
Mapping to an ML problem:ML problem formulation. 00:00:00
Mapping to an ML problem:Performance metrics. 00:00:00
Hamming loss 00:00:00
EDA:Data Loading 00:00:00
EDA:Analysis of tags 00:00:00
EDA:Data Preprocessing 00:00:00
Data Modeling : Multi label Classification 00:00:00
Data preparation. 00:00:00
Train-Test Split 00:00:00
Featurization 00:00:00
Logistic regression: One VS Rest 00:00:00
Sampling data and tags+Weighted models. 00:00:00
Logistic regression revisited 00:00:00
Why not use advanced techniques 00:00:00
Case study 6: Microsoft Malware Detection
Business/Real world problem:Problem definition 00:00:00
Business/real world problem :Objectives and constraints 00:00:00
Machine Learning problem mapping :Data overview. 00:00:00
Machine Learning problem mapping :ML problem 00:00:00
Machine Learning problem mapping :Train and test splitting 00:00:00
Exploratory Data Analysis :Class distribution. 00:00:00
Exploratory Data Analysis :Feature extraction from byte files 00:00:00
Exploratory Data Analysis :Multivariate analysis of features from byte files 00:00:00
Exploratory Data Analysis :Train-Test class distribution 00:00:00
ML models – using byte files only :Random Model 00:00:00
k-NN 00:00:00
Logistic regression 00:00:00
Random Forest and Xgboost 00:00:00
ASM Files :Feature extraction & Multiprocessing. 00:00:00
File-size feature 00:00:00
Univariate analysis 00:00:00
t-SNE analysis. 00:00:00
ML models on ASM file featuresML models on ASM file features 00:00:00
Models on all features :t-SNE 00:00:00
Models on all features :RandomForest and Xgboost 00:00:00
Unsupervised Learning/Clustering
Unsupervised learning 00:00:00
Applications 00:00:00
Metrics for Clustering 00:00:00
K-Means: Geometric intuition, Centroids 00:00:00
K-Means: Mathematical formulation: Objective function 00:00:00
K-Means Algorithm. 00:00:00
How to initialize: K-Means++ 00:00:00
Failure cases/Limitations 00:00:00
K-Medoids 00:00:00
Determining the right K 00:00:00
Code Samples 00:00:00
Time and Space Complexity 00:00:00
Hierarchical Clustering Technique
Agglomerative & Divisive, Dendrograms 00:00:00
Agglomerative Clustering 00:00:00
Proximity methods: Advantages and Limitations. 00:00:00
Time and Space Complexity 00:00:00
Limitations of Hierarchical Clustering 00:00:00
Code sample 00:00:00
DBSCAN (Density Based Clustering) Technique
Density based clustering 00:00:00
MinPts and Eps: Density 00:00:00
Core, Border and Noise points 00:00:00
Density edge and Density connected points. 00:00:00
DBSCAN Algorithm 00:00:00
Hyper Parameters: MinPts and EpsA 00:00:00
Advantages and Limitations of DBSCAN 00:00:00
Time and Space Complexity 00:00:00
Code samples. 00:00:00
Recommender Systems and Matrix Factorization
Content based vs Collaborative Filtering 00:00:00
Similarity based Algorithms 00:00:00
Matrix Factorization: PCA, SVD 00:00:00
Matrix Factorization: NMF 00:00:00
Matrix Factorization for Collaborative filtering 00:00:00
Matrix Factorization for feature engineering 00:00:00
Clustering as MF 00:00:00
Hyperparameter tuning 00:00:00
Matrix Factorization for recommender systems: Netflix Prize Solution 00:00:00
Cold Start problem 00:00:00
Word vectors as MF 00:00:00
Eigen-Faces 00:00:00
Code example 00:00:00
Case Study 8: Amazon Fashion Discovery Engine (Content Based Recommendation)
Problem Statement: Recommend similar apparel products in e-commerce using product descriptions and Images 00:00:00
Plan of action 00:00:00
Amazon product advertising API 00:00:00
Data folders and paths 00:00:00
Overview of the data and Terminology 00:00:00
Understand duplicate rows 00:00:00
Remove duplicates : Part 1 00:00:00
Remove duplicates: Part 2 00:00:00
Text Pre-Processing: Tokenization and Stop-word removal 00:00:00
Stemming 00:00:00
Text based product similarity :Converting text to an n-D vector: bag of words 00:00:00
Code for bag of words based product similarity 00:00:00
TF-IDF: featurizing text based on word-importance 00:00:00
Code for TF-IDF based product similarity 00:00:00
Code for IDF based product similarity 00:00:00
Text Semantics based product similarity: Word2Vec(featurizing text based on semantic similarity) 00:00:00
Code for Average Word2Vec product similarity 00:00:00
TF-IDF weighted Word2Vec 00:00:00
Code for IDF weighted Word2Vec product similarity 00:00:00
Weighted similarity using brand and color 00:00:00
Code for weighted similarity 00:00:00
Building a real world solution 00:00:00
Deep learning based visual product similarity:ConvNets: How to featurize an image: edges, shapes, parts 00:00:00
Using Keras + Tensorflow to extract features 00:00:00
Visual similarity based product similarity 00:00:00
Measuring goodness of our solution :A/B testing 00:00:00
Assignment-24: Apparel Recommendation 00:00:00
Case Study 9: Netflix Movie Recommendation System (Collaborative Based Recommendation)
Business/Real world problem:Problem definition 00:00:00
Objectives and constraints 00:00:00
Mapping to an ML problem:Data overview. 00:00:00
Mapping to an ML problem:ML problem formulation 00:00:00
Exploratory Data Analysis:Data preprocessing 00:00:00
Exploratory Data Analysis:Temporal Train-Test split. 00:00:00
Exploratory Data Analysis:Preliminary data analysis. 00:00:00
Exploratory Data Analysis:Sparse matrix representation 00:00:00
Exploratory Data Analysis:Average ratings for various slices 00:00:00
Exploratory Data Analysis:Cold start problem 00:00:00
Computing Similarity matrices:User-User similarity matrix 00:00:00
Computing Similarity matrices:Movie-Movie similarity 00:00:00
Computing Similarity matrices:Does movie-movie similarity work? 00:00:00
ML Models:Surprise library 00:00:00
Overview of the modelling strategy. 00:00:00
Data Sampling. 00:00:00
Google drive with intermediate files 00:00:00
Featurizations for regression. 00:00:00
Data transformation for Surprise. 00:00:00
Xgboost with 13 features 00:00:00
Surprise Baseline model. 00:00:00
Xgboost + 13 features +Surprise baseline model 00:00:00
Surprise KNN predictors 00:00:00
Matrix Factorization models using Surprise 00:00:00
SVD ++ with implicit feedback 00:00:00
Final models with all features and predictors. 00:00:00
Comparison between various models. 00:00:00
Deep Learning: Neural Networks
History of Neural networks and Deep Learning. 00:00:00
How Biological Neurons work? 00:00:00
Growth of biological neural networks 00:00:00
Diagrammatic representation: Logistic Regression and Perceptron 00:00:00
Multi-Layered Perceptron (MLP). 00:00:00
Notation 00:00:00
Training a single-neuron model. 00:00:00
Training an MLP: Chain Rule 00:00:00
Training an MLP:Memoization 00:00:00
Backpropagation. 00:00:00
Activation functions 00:00:00
Vanishing Gradient problem. 00:00:00
Bias-Variance tradeoff. 00:00:00
Decision surfaces: Playground 00:00:00
Deep Learning: Deep Multi-Layer Perceptrons
Deep Multi-layer perceptrons:1980s to 2010s 00:00:00
Dropout layers & Regularization. 00:00:00
Rectified Linear Units (ReLU). 00:00:00
Weight initialization. 00:00:00
Batch Normalization. 00:00:00
Optimizers:Hill-descent analogy in 2D 00:00:00
Optimizers:Hill descent in 3D and contours. 00:00:00
SGD Recap 00:00:00
Batch SGD with momentum. 00:00:00
Nesterov Accelerated Gradient (NAG) 00:00:00
Optimizers:AdaGrad 00:00:00
Optimizers : Adadelta andRMSProp 00:00:00
Adam 00:00:00
Which algorithm to choose when? 00:00:00
Gradient Checking and clipping 00:00:00
Softmax and Cross-entropy for multi-class classification. 00:00:00
How to train a Deep MLP? 00:00:00
Auto Encoders. 00:00:00
Word2Vec :CBOW 00:00:00
Word2Vec: Skip-gram 00:00:00
Word2Vec :Algorithmic Optimizations. 00:00:00
Deep Learning: Tensorflow and Keras
Tensorflow and Keras overview 00:00:00
GPU vs CPU for Deep Learning. 00:00:00
Google Colaboratory. 00:00:00
Install TensorFlow 00:00:00
Online documentation and tutorials 00:00:00
Softmax Classifier on MNIST dataset. 00:00:00
MLP: Initialization 00:00:00
Model 1: Sigmoid activation 00:00:00
Model 2: ReLU activation. 00:00:00
Model 3: Batch Normalization. 00:00:00
Model 4 : Dropout. 00:00:00
MNIST classification in Keras. 00:00:00
Hyperparameter tuning in Keras. 00:00:00
Deep Learning: Convolutional Neural Nets
Biological inspiration: Visual Cortex 00:00:00
Convolution:Edge Detection on images. 00:00:00
Convolution:Padding and strides 00:00:00
Convolution over RGB images. 00:00:00
Convolutional layer. 00:00:00
Max-pooling. 00:00:00
CNN Training: Optimization 00:00:00
Receptive Fields and Effective Receptive Fields 00:00:00
Example CNN: LeNet [1998] 00:00:00
ImageNet dataset. 00:00:00
Data Augmentation. 00:00:00
Convolution Layers in Keras 00:00:00
AlexNet 00:00:00
VGGNet 00:00:00
Residual Network. 00:00:00
Inception Network. 00:00:00
What is Transfer learning. 00:00:00
Code example: Cats vs Dogs. 00:00:00
Code Example: MNIST dataset. 00:00:00
Deep Learning: Long Short-term memory (LSTMs)
Why RNNs? 00:00:00
Recurrent Neural Network. 00:00:00
Training RNNs: Backprop. 00:00:00
Types of RNNs. 00:00:00
Need for LSTM/GRU. 00:00:00
LSTM. 00:00:00
GRUs. 00:00:00
Deep RNN. 00:00:00
Bidirectional RNN. 00:00:00
Code example : IMDB Sentiment classification 00:00:00
Case Study 11: Human Activity Recognition
Human Activity Recognition Problem definition 00:00:00
Dataset understanding 00:00:00
Data cleaning & preprocessing 00:00:00
EDA:Univariate analysis. 00:00:00
EDA:Data visualization using t-SNE 00:00:00
Classical ML models. 00:00:00
Deep-learning Model. 00:00:00
Case Study 10: Self Driving Car
Self Driving Car :Problem definition. 00:00:00
Datasets. 00:00:00
Data understanding & Analysis :Files and folders. 00:00:00
Dash-cam images and steering angles. 00:00:00
Split the dataset: Train vs Test 00:00:00
EDA: Steering angles 00:00:00
Mean Baseline model: simple 00:00:00
Deep-learning model:Deep Learning for regression: CNN, CNN+RNN 00:00:00
Batch load the dataset. 00:00:00
NVIDIA’s end to end CNN model. 00:00:00
Train the model. 00:00:00
Test and visualize the output. 00:00:00
Extensions. 00:00:00
Case Study 10: Music Generation using Deep-Learning
Real-world problem 00:00:00
Music representation 00:00:00
Char-RNN with abc-notation :Char-RNN model 00:00:00
Char-RNN with abc-notation :Data preparation. 00:00:00
Char-RNN with abc-notation:Many to Many RNN ,TimeDistributed-Dense layer 00:00:00
Char-RNN with abc-notation : State full RNN 00:00:00
Char-RNN with abc-notation :Model architecture,Model training. 00:00:00
Char-RNN with abc-notation :Music generation. 00:00:00
Char-RNN with abc-notation :Generate tabla music 00:00:00
MIDI music generation. 00:00:00
Survey blog: 00:00:00

Course Reviews

N.A

ratings
  • 5 stars0
  • 4 stars0
  • 3 stars0
  • 2 stars0
  • 1 stars0

No Reviews found for this course.

PRIVATE COURSE
  • PRIVATE
  • 1 week, 3 days
0 STUDENTS ENROLLED
    Copyright @2019