Machine Learning Course Content

Overview of Data

• BI versus Data Science
• Drivers of Big Data
• Emerging Big Data Ecosystem and new Analytics
• Data Analytics Life Cycle
• Common Tools for Model building

Introduction to Machine Learning

• What is machine learning and it use cases
• Brief overview of descriptive statistics types of variable
• Types of machine learning – choice of algorithm
• Machine Learning using Python

Introduction to Numpy

• Fast element-wise array functions using numpy arrays
• Data processing using numpy arrays
• Linear Algebra – matrix multiplication, decompositions/factorization determinants

Introduction to Pandas

• Load data into Pandas Dataframe
• Indexing, selection, filtering, sorting, and grouping
• Arithmetic operations
• Handle Missing Data
• Correlation and covariance
• Unique values
• Value count
• Distribution

Data Visualization using Matplotlib and Seaborn

• Line plots
• Bar plots
• Histograms and density plots
• Scatter plots
• Step
• Heat maps
• Colors, styles, labels, legends
• Using Seaborn for color pallets

Linear Regression

• Understanding the cost function and minimize cost function using gradience descent algorithm
• Finding best fit lines with linear regression
• Model evaluation metrics – R2, RMSE, MAE, F-stat
• Shrinking coefficients to understand the data – Ridge regression, Lasso regression, forward stage-wise regression, L1/L2 Penalty for regularization
• Bias / variance trade off
• Tree based regression (CART regression)

Model Tuning

• Combining transformers and estimators in a pipeline
• Using k-fold cross validation to assess model performance
• Debugging algorithms with learning and validation curve
• Diagnosis bias and variance problems with learning curves
• Fine tuning hyper parameters using grid search

Classification Algorithm

• Overview of Perceptron, Analine, Stochastic Gradient Descent, MiniBatch Gradient descent for classification problems
• Logistic Regression for binary and multi class classification – One-vs-all patterns
• Classification using decision trees, random forest
• Classifying with KNN
• Model evaluation using accuracy score, precision, recall, F-score, ROC plot, AUC, confusion matrix Tune the hyper parameters using cross validation and grid search

Feature Engineering

• Curse of dimensionality
• Dimensionality reduction techniques:-feature selection, feature compression
• Using regularization
• Using random forest feature importance
• Using PCA to compress feature into smaller subspace
• Using PCA kernel trick to tackle non-linear feature space
• Using SDV to compress data

Clustering

• Working with unlabeled data – clustering analysis
• K-means clustering
• Hard (K-means) vs Soft clustering (Fuzzy c-means)
• Find optimal number of clusters
• Hierarchical Clustering
• DBSCAN

ML Pipeline

• Building machine learning pipeline
• Tuning pipeline using grid search
• Extracting best estimators from the pipeline

Ensemble Techniques

• Putting multiple models in action
• Building a hybrid model and compare performance metrics

Learning Curve

• How much data is sufficient to train a model?
• Detect whether a model reached saturation

Deployment of Machine Learning

• Production readiness of ML application
• Offline learning, online prediction
• Online learning
• Exposing ML model as web service

Intro to Deep Learning

• What is Artificial Neural Network?
• What is deep learning?
• Convolutional Neural Networks (CNN) and its use cases
• Recurrent Neural Networks (RNN) and its use cases
• Computer Vision – classification of MNIST dataset
• Symbolic Computation and Tensor Flow for deep learning system

FAQ’S

What if I miss one (or) more class?

No need to worry about the classes you missed. We will definitely guide you by having optional classes or by having classes with other batches with the same topic you missed previous classes.

Who is my instructor?

IT professionals who have strong knowledge in technical know how to convey things with the real-time example. Even a layman could understand the concepts which given by our experts.

What are the modes of training offered for this course?

We offer this course in “Live Instructor-Led Online Training” mode. Through this way you won’t mess anything in your real-life schedule. You will be shared with live meeting access while your session starts.

What are the system requirements to work?

Minimum 2GB RAM and i3 processor is required

Can I attend a demo session?

You can get a sample class recording to ensure you are in right place. We ensure you will be getting complete worth of your money by assigning a best instructor in that technology.

How about group discounts (or) corporate training for our team?

We are absolutely loved to talk in-person about group training (or) corporate training. So, please get in touch with our team through “Quick Enquiry”, “Live Chat” or “Request Call-back” channels.

Where do Our Online learners and Trainer’s come from

We are providing online training, One-to-One training with the help of experts. Our learners and trainers are frequently coming from different countries like USA, India, UK, Australia, New Zealand, Canada and UAE. To specify in cities London, Bangalore, California, New York, Pune, Mumbai, Chennai, New Delhi, San Francisco, New Jersey, Texas, Florida, Kolkata, Gurgaon, Berlin and Hyderabad among many.

I have more queries?

If you want to know More Details about Online Training Please Contact us. Or you can share your quires through info@monstercourses.com. Estimated turnaround time will be 24 hours for mails.

Contact us