Machine Learning and Deep Learning

Become a " Machine Learning and Deep Learning" Specialist. In this learning path, you will learn " Basic Data Manipulation, Dimensionality Reduction Techniques, Supervised Learning Algorithms, Unsupervised Learning Algorithms, Deep Neural Network, Foundation of CNN, and Many More".

1000+ Students enrolled
Flexible Learning

Learn at your own pace and reach your personal goals on the schedule that works best for you.

Real-world Projects

You’ll master the in-demand technologies by building real-world projects.

Live Mentor Workshops

You’ll have access to free live mentor workshop sessions through out your subscription period.

Verifiable Certificate

Upon successful completion of the Course, You will receive a Verifiable certificate with QR code.

Quiz & Mock Tests

Assess your knowledge with quiz's, mock tests and interviews.

Assured Internship

Upon successful completion of this course you are eligible to grab an internship opportunity.

Machine Learning and Deep Learning

Become a " Machine Learning and Deep Learning" Specialist. In this learning path, you will learn " Basic Data Manipulation, Dimensionality Reduction Techniques, Supervised Learning Algorithms, Unsupervised Learning Algorithms, Deep Neural Network, Foundation of CNN, and Many More".

Login to Subscribe
Includes:
  • Verifiable certificate
  • Quiz & mock tests
  • Live mentor workshops
  • 2 devices access*
Course Description

Welcome to " Machine Learning and Deep Learning"

In this course you will be learning “Basic Data Manipulation,  Dimensionality Reduction Techniques, Supervised Learning Algorithms, Unsupervised Learning Algorithms, Deep Neural Network, Foundation of CNN, and Many More”. We'll take you step-by-step through engaging video tutorials and teach you everything you need to know to succeed in the industry. This course has a tremendous amount of content and resources so that you can learn everything you need to know - whatever is appropriate for your ability level. You will be able to learn at your own pace. You will always be able to come back to the content to review it or learn additional concepts when you are ready for them. You will get great value from this course and, more importantly, you will have a great time learning.

Happy Learning

What you will learn?
  • Basic Data Manipulation
  • Handling Numerical Data
  • Handling Categorical Data
  • Handling Dates and Times
  • Dimensionality Reduction
  • Supervised Learning
  • k-Nearest Neighbors
  • Linear Model
  • Decision Tree and Random Forest
  • Kernelized Support Vector Machines
  • Unsupervised Learning
  • Dimensionality Reduction
  • Feature Extraction and Manifold Learning
  • Clustering
  • Introduction to Neural Networks
  • Improving Deep Neural Networks
  • Optimization Algorithms
  • Convolutional Neural Network
  • Foundations of CNN
  • Deep Convolutional Model
  • Special Application
  • Introduction to RNNs
  • Different Types of RNNs
  • Brief Introduction of GRU and LSTM
Requirements
  • No Prerequisites Required
Course Curriculum
  • Module - 1: Machine Learning
    Go Zero-One by learning the much-needed fundamentals of “Machine Learning". In this course, you will learn " Dimensionality Reduction Techniques, Supervised Learning Algorithms, Unsupervised Learning Algorithms, Model Evaluation Metrics".
    Section 1: Basic Data Manipulation
    12 Lessons
    • Lets start with Creating DataFrame
    • Describing the Data
    • Navigating the Dataframe
    • Selecting Rows Based On Conditionals
    • Replacing Values
    • Renaming Columns
    • Finding the Minimum,Maximum,Sum,Average.Count,Kurtosis and Skewness
    • Finding Unique Values
    • Deleting Columns And Rows
    • Looping And Applying Function Over a Column
    • Concatenating or Merging Data Frames
    • Grouping Rows By Values
    • Basic Numerical Feature Processing
    • Binning Features
    • Detecting and Handling Outliers
    • Scaling Feature and Handling Missing Values
    • Converting String To Dates
    • Date Based Features
    • Time Based Feature
    • Categorical Encoding and Its Need
    • Encoding Categorical Features
    • Frequency Encoding
    • Linear Principal Component Analysis
    • Kernel Principal Component Analysis
    • Thresholding Numerical Feature Variance
    • Handeling Highly Correlated Features
    • Automatic Feature Selection
  • Module - 2: Supervised Learning Algorithms
    Go Zero-One by learning the much-needed fundamentals of “Supervised Learning Algorithms". In this course, you will learn " Basics of Supervised Learning, k-Nearest Neighbors, Linear Model, Decision Tree, and Random Forest ".
    Section 1: Basics of Supervised Learning
    3 Lessons
    • What is classification and Regression.
    • Bais Vs. Variance
    • What is Generalization, Overfitting And Underfitting
    • K-Nearest Neighbor Classifier
    • K-Nearest Neighbor Regression
    • Strength, Weakness And Parameters.
    • Ordinary Least Square
    • Regularization
    • Ridge and Lasso Regression
    • Logistic Regression and LinearSVC
    • Logistic Regression and LinearSVC
    • Decision Tree
    • Kernel Trick
  • Module - 3: Unsupervised Learning Algorithms
    Go Zero-One by learning the much-needed fundamentals of “Unsupervised Learning Algorithms". In this course, you will learn " Basics Of Unsupervised Learning, Dimensionality Reduction, Clustering".
    Section 1: Basics Of Unsupervised Learning
    2 Lessons
    • Types Of Unsupervised Learning
    • Challenges in Unsupervised Learning
    • Eigenfaces for Feature Extraction using PCA
    • Non-Negative Matrix Factorization and its Application
    • t-SNE And Manifold Learning with t-SNE
    • K-Means Clustering
    • Failure Of K-Means Clustering
    • K-Means Clustering Using Mean Shift
    • K-Means Clustering Using Mean Shift
    • Hierarvhicalor Agglomerative Clustering using Dendrogram
  • Module - 4: Model Evaluation Metrics
    Go Zero-One by learning the much-needed fundamentals of “Model Evaluation Metrics". In this course, you will learn " Classification Metrics and Regression Metrics".
    Section 1: Classification Metrics
    2 Lessons
    • Confusion Matrix
    • AUC-ROC
    • Mean Absolute Error
    • Root Mean Squared Error
  • Module - 5: Hyperparameter Optimization Techniques
    Go Zero-One by learning the much-needed fundamentals of “Hyperparameter Optimization Techniques". In this course, you will learn " K-Fold Cross-Validation, Selecting Best Model using Exhaustive Search".
    Section 1: Hyperparameter Optimization Techniques
    5 Lessons
    • K-Fold Cross Validation
    • Selecting Best Model Using Exhaustive Search
    • Selecting Best Model Using Randomized Search
    • Selecting Best Model From Multiple Learning Algorithms
    • Selecting Best Model When Preprocessing
  • Module - 6: Deep Learning
    Go Zero-One by learning the much-needed fundamentals of “Deep Learning". In this course, you will learn " Neural Network, Deep Neural Networks, Optimization Algorithms, Foundation of CNN".
    Section 1: Introduction to Neural Network
    12 Lessons
    • Neural Network Representation
    • Computing a Neural Network's Output
    • Activation functions
    • Derivatives of activation functions
    • What is Neural Networks.
    • Revisiting Binary Classification And Logistic Regression
    • Gradient Descent
    • Computation Graph and It's Derivative
    • Gradient descent for Logistic Regression
    • Gradient Descent Over m Training Examples
    • Vectorization
    • Vectorization Of Logistic Regression
    • Deep L-layer neural network
    • Forward Propagation in Deep Networks
    • Dropout Regularization
    • Normalizing Input
    • Vanishing_Exploding Gradients
    • RMS Convolution
    • Learning Rate Decay
    • Why Convolution
    • Edge Detection Example
    • Padding
    • Strided Convolutions
    • Convolution Over Volume
    • One Layer Of Convolutional Network
    • Simple Convolutional Network Example
    • Pooling Layers
    • Classic Networks
    • ResNet
    • Transfer Learning
    • Data Augmentation
    • Neural Style Transfer
    • Introduction to RNN's
    • Different Types of RNN's
    • Brief Introduction of GRU and LSTM
  • Certificate
    Once you've successfully completed the course, You will receive the certificate

Get Certified! Get Recognized…

Upon successful completion of the Course, You will receive a Verifiable certificate with QR code. Now employers can verify the certificates just by scanning QR code or by verification ID.

Differentiate yourself

The knowledge and skills you've gained working on projects, simulations, case studies will set you ahead of competition.

Share your achievement

Talk about it on Linkedin, Twitter, Facebook, boost your resume or frame it - tell your friends about it.

Learn

Learn in-demand technology skills through immersive content.

Practice

Practice the tech skills and build real-world projects for your portfolio.

Apply

Apply your knowledge in hackathons to grab internships and placements.

Assess

Assess your knowledge with quiz's, mock tests and interviews.

What our students say about SkillLauncher

Happy Students & Feedbacks

Ajeet Deshpande

Student

Great learning platform for all type of learners, New trending courses with new teaching methods, really good work. Thanks SkillLauncher!

Pravin Pratap Basu

Student

Support on the courses is very good. Apart from that course materials are also good . Teaching faculties are also extremly supportive.

Basanti Mahal

Student

The courses are very good and well structured. SkillLauncher even covered more advanced topics which was not in agenda or course content.

Anil Prasad

Student

These guys rock with amount of patience, knowledge and love how to explain things and cannot thank enough for the extreme support and mentoring.

Rama Krishna

Student

Content of courses is amazing. No other online platform has as many courses with dedicated teaching assistance. It has some free tutorials with time access.

Pirzada Gagrani

Student

I was searching for a platform to learn AI/ML course and I came across this SkillLauncher. Their support was awesome from the day of enrollment.

Sign in with Google