Machine Learning Course ( Coding Ninjas )

Projects that you will get going..

Tendency Descent Implementation

Execute the standard Gradient Descent computation for headway of a model (Regression or Neural)

Vital Regression Implementation

Execute the standard Logistic Regression model usually used for orchestrating data into twofold classes like pass/misfire, win/lose, alive/dead or sound/crippled.

Decision Tree Implementation

Execute the standard Decision Tree Class used for describing data into various classes using a tree-like model of decisions and their expected outcomes.

Picture Caption Generation

Gather a CNN/LSTM based model to give a caption to the given picture.

Involved Driver Detection

Manufacture a plan model to anticipate using a data base of pictures whether a given driver is redirected, ie, informing, on a call, driving safely, etc

Text Generation

Collect a Neural Network based model to predict what the accompanying word will be in a gathering of words/sentences

Brain Machine Translation

Develop a general model with the ultimate objective of translation of articulations and pictures starting with one language then onto the next using Artificial Neural Network.

Metropolitan Sound Classification

Gather a Neural association based model to portray various sounds using their uncommon spectrogram into classes like Dog Barking, Sirens, Street Music, etc

Text Classification

Gather a classifier model using Naive Bayes estimation to expect the subject of an article present in a paper

Picture Classification (CIFAR-10 Dataset)

Integrate a classifier for describing 10,000 pictures into 10 classes (canine, pony, cat, etc) using the CIFAR-10 Dataset.

Twitter Sentiment Analysis

Separate the tweets introduced on twitter on expect the assessment of the tweet for instance certain, negative or fair-minded

Facial Emotion Recognition

Build a general model with the ability to expect the facial sensation of a person in an image.

Develop Facial Emotion Recognition, Distracted Driver Detection activities and astonish determination delegates to get extraordinary positions

Course Curriculum

Show

Introduction TO MACHINE LEARNING

Introduction to Machine Learning, Supervised Learning, Steps for Supervised getting Loading Boston Dataset, Training an Algorithm

Immediate and Logistic Regression

Introduction TO LINEAR REGRESSION

Introduction to Linear Regression, Optimal Coefficients, Cost work, Coefficient of Determination, Analysis of Linear Regression using hoax Data, Linear Regression Intuition

MULTIVARIABLE REGRESSION AND GRADIENT DESCENT

Customary Gradient Descent, Learning Rate, Complexity Analysis of Normal Equation Linear Regression, How to find More Complex Boundaries, Variations of Gradient Descent

PROJECT

Incline Descent

Key REGRESSION

Managing Classification Problems, Logistic Regression, Cost Function, Finding Optimal Values, Solving Derivatives, Multiclass Logistic Regression, Finding Complex Boundaries and Regularization, Using Logistic Regression from Sklearn

Decision Trees and Random Forests

• Decision TREES - 1

Decision Trees, Decision Trees for Interview call, Building Decision Trees, Getting to Best Decision Tree, Deciding Feature to Split on, Continuous Valued Features

• Decision TREES - 2

Code using Sklearn decision tree, information gain, Gain Ratio, Gini Index, Decision Trees and Overfitting, Pruning

PROJECT

Decision Tree Implementation

Unpredictable FORESTS

Introduction to Random Forests, Data Bagging and Feature Selection, Extra Trees, Regression using decision Trees and Random Forest, Random Forest in Sklearn

• Guiltless Bayes

• Guiltless BAYES

Bayes Theorem, Independence Assumption in Naive Bayes, Probability appraisal for Discrete Values Features, How to manage zero probabilities, Implementation of Naive Bayes, Finding the probability for predictable regarded components, Text Classification using Naive Bayes

PROJECT

• Text Classification

• K-NEAREST Neighbors

Preface to KNN, Feature scaling before KNN, KNN in Sklearn, Cross Validation, Finding Optimal K, Implement KNN, Curse of Dimensionality, Handling Categorical Data, Pros and Cons of KNN

 

KNN and SVM

SUPPORT VECTOR MACHINE

Sense behind SVM, SVM Cost Function, Decision Boundary and the C limit, using SVM from Sklearn, Finding Non Linear Decision Boundary, Choosing Landmark Points, Similarity Functions, How to move to new perspectives, Multi-class Classification, Using Sklearn SVM on Iris, Choosing Parameters using Grid Search, Using Support Vectors to Regression

Head Component Analysis

• PCA - 1

Sense behind PCA, Applying PCA to 2D data, Applying PCA on 3D data, Math behind PCA, Finding Optimal Number of Features, Magic behind PCA

• PCA - 2

PCA on Images, PCA on Olevitti Images, Reproducing Images, Eigenfaces, Classification of LFW Images

PROJECT

Cifar10

Customary Language Processing

NLP - 1

Using Words as Features, Basics of word dealing with, Stemming, Part of Speech, Lemmatization, Building Feature set, Classification using NLTK Naive Bayes

NLP - 2

Using Sklearn classifiers inside NLTK, Countvectorizer, Sklearn Classifiers, N-gram, TF-IDF

PROJECT

Twitter Sentiment Analysis

Brain Networks

Brain NETWORKS - 1

Why do we need Neural Networks, Example with Linear Decision Boundary, Finding Non-Linear Decision Boundary, Neural Network Terminology, No of Parameters in Neural Network, Forward and Backward Propagation, Cost Function, How to manage Multiclass request, MLP classifier in sklearn

Brain NETWORKS - 2

Forward Propagation, Error Function in Gradient drop, Derivative of Sigmoid Function, Math behind Backpropagation, Implementing a clear Neural Network, Optimizing the code using Vector Operations, Implementing a generally Neural Network.

TensorFlow and Keras

TENSORFLOW

Preamble to TensorFlow, Constants, Session, Variables, Placeholder, MNIST Data, Initialising Weights and Biases, Forward Propagation, Cost Function, Running the Optimiser, How achieves the Optimiser work?, Running Multiple Iterations, Batch Gradient Descent

KERAS

Preamble to Keras, Flow of code in Keras, Kera Models, Layers, Compiling the model, Fitting Training Data in Keras, Evaluations and Predictions

Convolutional Neural Network

CNN - 1

Issue in Handling pictures, Convolution Neural Networks, Stride and Padding, Channels, Pooling Layer, Data Flow in CNN

CNN - 2

Plan of CNN, Initializing loads, Forward Propagation in TensorFlow, Convolution and Maxpool Functions, Regularization using Dropout layer, Adding Dropout Layer to the association, Building CNN Keras

RNN and LSTM

Redundant NEURAL NETWORK

Building ML Models for back to back Data, Recurrent Neural Networks, How achieves RNN work, Typical RNN Structures, Airline Data Analysis, Preparing Data for RNN, Setting up the RNN model, Analyzing the Output

LONG SHORT TERM MEMORY

Dissipating or Exploiting Gradients, Gated Recurrent Units, Variations of the GRU, LSTM

Independent Learning

Independent LEARNING - 1

Preamble to Unsupervised Learning, Introduction to Clustering, Using K-infers for Flat Clustering, KMeans Algorithm, Using KMeans from Sklearn, Implementing Fit and Predict Functions, Implementing K-Means Class

Independent LEARNING - 2

Bit by bit directions to pick Optimal K, Silhouette estimation to pick K, Introduction to K Medoids, K Medoids Algorithm, Introduction to Hierarchical Clustering, Top down/Divisive Approach, Bottom up/Divisive Approach