Machine Learning & Deep Learning in Python

Machine Learning & Deep Learning with Python is an in-depth course designed to provide a comprehensive understanding of the fundamental concepts and practical applications of machine learning and deep learning using the Python programming language. This course covers the theory, algorithms, and tools required to build and deploy machine learning models for various real-world applications.

Course Objectives:
  1. Understand the Fundamentals: Gain a strong foundation in machine learning and deep learning principles, including supervised and unsupervised learning, neural networks, and deep learning architectures.
  2. Hands-on Experience: Develop practical skills in Python programming for machine learning and deep learning, including data preprocessing, model training, and evaluation.
  3. Apply Algorithms: Learn to apply a variety of machine learning and deep learning algorithms, such as regression, classification, clustering, and convolutional and recurrent neural networks.
  4. Data Handling: Master data preparation techniques, including data cleaning, feature engineering, and working with different data types.
  5. Model Evaluation: Explore methods for evaluating and fine-tuning machine learning models to ensure optimal performance.
  6. Real-World Applications: Explore real-world applications of machine learning and deep learning, such as image recognition, natural language processing, and recommendation systems.
  7. Tools and Frameworks: Familiarize yourself with popular Python libraries and frameworks, such as scikit-learn, TensorFlow, and Keras, for building and deploying machine learning models.
  8. Ethical Considerations: Discuss ethical and responsible AI practices, including bias, fairness, and privacy concerns in machine learning applications.
  9. Project Work: Apply your knowledge through hands-on projects, building and deploying machine learning models on real datasets.

Course Prerequisites:
  • Python Basic
  • Basic Mathematics and Statistics
  • Programming Experience

Target Audience:

 This course is suitable for individuals with a variety of backgrounds, including but not limited to:
  • Data Analysts and Data Scientists looking to enhance their machine learning skills.
  • Software Developers interested in transitioning to machine learning and deep learning roles.
  • Business and IT professionals seeking to understand the practical applications of AI and machine learning in their industries.
  • Researchers and academics exploring the latest advancements in machine learning and deep learning.
  • Enthusiasts and hobbyists interested in diving into the world of AI and data science.

By the end of this course, participants will have the knowledge and practical skills necessary to work on machine learning and deep learning projects and integrate these techniques into their professional or academic endeavors.

Course Summary

Course Fee

৳ 15,000

Training Method

Offline/Online

Total Modules

3

Course Duration

72 Hours

Total Session

36

Class Duration

2 Hours

Enroll Now

Details Course Outlines - Machine Learning

Module-01

Programming with Python and Related Libraries of MachineLearning

  • 1.1 Introduction to Python and Programming Fundamentals
  • Basic syntax of Python and data types
  • Variables, Basic arithmetic and logical operations
  • Hands-on exercises for basic data type and variable operations
  • 1.2 Conditional Statement in Python
  • Syntax of if statements
  • Syntax of if-else statements
  • Syntax of nested if statements
  • Syntax of elif statements
  • 1.3 Introduction to Iteration and Advanced Iteration Techniques
  • Basic syntax and examples of for and while loop in Python
  • Nested Loops and their applications, Loop control statements (i.e., break and continue)
  • Range function and its usage in loops
  • 1.4 Introduction to Python Functions
  • Overview of functions in Python, Creating and calling a function
  • Function arguments and parameters, Default parameters
  • Importing modules and libraries, Using functions fromlibraries
  • Understanding the Python standard library and popular third-party libraries
  • 1.5 Data Structures
  • Understanding the difference between lists and tuples, Creating, indexing and slicing lists and tuples
  • Introduction to dictionaries and their use, Common dictionary methods like keys(), values(), items() and so on.
  • Introduction to sets, Set operations: union(), intersection(), difference() and symmetric_difference()
  • 1.6 Concepts of Machine Learning Related Libraries of Python
  • Introduction to Numpy arrays and their use.
  • Introduction to Pandas DataFrames and their use
  • Introduction to Matplotlib for data visualization
  • Overview to scikit-learn for machine learning algorithms

Module-02

Traditional Machine Learning Algorithms and Projects

  • 2.1 Background of Machine Learning
  • Overview of Machine Learning
  • Categories of Machine Learning Algorithm
  • Parametric and Non-Parametric Machine Learning Algorithm
  • Supervised, Unsupervised and Semi-supervised Learning
  • Difference among Regression, Classification, Clustering and Dimensionality Reduction Technique inMachine Learning
  • The Bias-Variance Trade-Off
  • Overfitting and Underfitting
  • How to Detect Overfitting and Underfitting?
  • Reasons for Overfitting anf Underfitting
  • How to Prevent Overfitting and Underfitting?
  • 2.2 Popular Machine Learning Algorithms
  • Linear Machine Learning Algorithms
  • Linear Regression
  • Logistic Regression
  • Linear Discriminant Analysis
  • Non-Linear Machine Learning Algorithms
  • Classification and Regression Trees
  • Naive Bayes
  • K Nearest Neighbour
  • K-Means
  • Linear Vector Quantization
  • Support Vector Machine
  • Ensemble Algorithms
  • Bagging and Random Forest
  • Boosting and AdaBoost
  • 2.3 Implementation of Machine Learning Algorithms in Python
  • How To Load Machine Learning Data
  • Load CSV File with NumPy
  • Load CSV File with Pandas
  • Understand Your Data with Descriptive Statistics
  • Peek the Data
  • Dimensions of the Data
  • Data Type of Each Attribute
  • Descriptive Statistics
  • Number of Class Distribution
  • Correlations between Attributes
  • Skew of Univariate Distributions
  • Understand Your Data with Visualization
  • Univariate Plots
  • Histogram
  • Density Plots
  • Box and Whisker Plots
  • Multivariate Plots
  • Correlation Matrix Plot
  • Scatter Plot Matrix
  • Data Pre-processing
  • Needs for Data Pre-processing
  • Rescale Data
  • Standardize Data
  • Normalize Data
  • Binarize Data (Make Binary)
  • Feature Selection for Machine Learning
  • Needs for Feature Selection
  • Univariate Selection
  • Recursive Feature Elimination
  • Principal Component Analysis
  • Feature Importance using Bagged decision trees
  • Train and Test Dataset Split
  • Split into Train and Test Sets
  • K-fold Cross Validation
  • Leave One Out Cross Validation
  • Repeated Random Test-Train Splits
  • Performance Matrix
  • Classification Metrics
  • Classification Accuracy
  • Logarithmic Loss
  • Area Under ROC Curve
  • Confusion Matrix
  • Classification Report
  • Regression Metrics
  • Mean Absolute Error
  • Mean Squared Error
  • R Squared Metric
  • Spot-Check Classification Algorithms
  • Linear Classification Algorithms
  • Logistic Regression
  • Linear Discriminant Analysis
  • Non-linear Classification Algorithms
  • k-Nearest Neighbors
  • Naive Bayes
  • Classification and Regression Trees
  • Support Vector Machines
  • Spot-Check Regression Algorithms
  • Linear Regression Algorithms
  • Linear Regression
  • Ridge Regression
  • LASSO Linear Regression
  • Elastic Net Regression
  • Non-linear Regression Algorithms
  • k-Nearest Neighbors
  • Classification and Regression Trees
  • Support Vector Machines
  • Compare Machine Learning Algorithms
  • Automate Machine Learning Workflows with Pipelines
  • Data Preparation and Modeling Pipeline
  • Feature Extraction and Modeling Pipeline
  • Performance Improvement with Ensembles
  • Combine Models Into Ensemble Predictions
  • Bagging Algorithms
  • Concepts of Begging
  • Algorithm
  • Random Forest
  • Boosting Algorithms
  • Concepts of Boosting Algorithm
  • AdaBoost
  • Voting Ensemble
  • Performance Improvement with Algorithm Tuning
  • Grid Search Parameter Tuning
  • Random Search Parameter Tuning

Module-03

Concepts and Uses of Deep Learning and Real Life Projects

  • 3.1 Basic of Biological Neural Networks and It’s Learning Process
  • Structure of Biological Neuron
  • Learning Process of Biological Neuron
  • 3.2 Pattern recognition, Feature vector and Feature Vector
  • Definition of Pattern Recognition
  • Block Diagram of Typical Pattern Recognition System
  • Feature Vector and Feature Space with Real Life Example
  • 3.3 Simulation Procedure of Biological Neuron into Machine
  • Outline of Basic Model of Biological Neuron
  • Overview of Thresholding Function
  • Single Layer Perceptron Learning Algorithm
  • Limitations of Single Layer Perceptron Learning Algorithm
  • 3.4 Multilayer Perceptron Neural Networks Algorithms
  • Architectural Overview of Multilayer Perceptron Neural Networks
  • Credit Assignment Problem, Characteristics of Linear andSigmoidal Thresholding Function
  • Algorithm Steps of Multilayer Perceptron Neural Networks Algorithm
  • How does Hidden Layer Act as a Feature Detector?
  • Visualizing Network Behaviour in 2D and 3D Form
  • Decision Boundaries or Regions Formed by introducingDifferent Number of Layers
  • 3.5 Deep Learning with Python
  • Deep Learning Libraries in Python
  • Introduction to Keras, Theano and TensorFlowBackends for Keras
  • Build Deep Learning Models with Keras
  • Develop the First Neural Network With Keras
  • Load Data
  • Define Model
  • Compile Model
  • Fit Model
  • Evaluate Model
  • Evaluate The Performance of Deep Learning Models
  • Empirically Evaluate Network Configurations
  • Data Splitting
  • Manual k-Fold Cross Validation
  • Use Keras Models With Scikit-Learn For General Machine Learning
  • Evaluate Models with Cross Validation
  • Grid Search Deep Learning Model Parameters
  • Project: Multiclass Classification Of Flower Species
  • Overview of Iris Flowers Classification Dataset
  • Import Classes and Functions
  • Initialize Random Number Generator
  • Load The Dataset
  • Encode The Output Variable
  • Define The Neural Network Model
  • Evaluate The Model with k-Fold Cross Validation
  • Project: Binary Classification Of Sonar Returns
  • Overview of Sonar Object Classification Dataset
  • Baseline Neural Network Model Performance
  • Improve Performance With Data Preparation
  • Tuning Layers and Neurons in The Model
  • Project: Regression Of Boston House Prices
  • Overview of Boston House Price Dataset
  • Develop a Baseline Neural Network Model
  • Lift Performance By Standardizing The Dataset
  • Tune The Neural Network Topology
  • Understand Model Behavior During Training By Plotting History
  • Access Model Training History in Keras
  • Visualize Model Training History in Keras
  • Reduce Overfitting With Dropout Regularization
  • Dropout Regularization For Neural Networks
  • Dropout Regularization in Keras
  • Using Dropout on the Visible Layer
  • Using Dropout on Hidden Layers
  • Lift Performance With Learning Rate Schedules
  • Learning Rate Schedule For Training Models
  • Ionosphere Classification Dataset
  • Time-Based Learning Rate Schedule
  • Drop-Based Learning Rate Schedule
  • Basic Concepts of Convolutional Neural Networks
  • The Case for Convolutional Neural Networks
  • Building Blocks of Convolutional Neural Networks
  • Convolutional Layers
  • Pooling Layers
  • Fully Connected Layers
  • Worked Example
  • Convolutional Neural Networks Best Practices
  • Project: Handwritten Digit Recognition
  • Overview of Handwritten Digit Recognition Dataset
  • Loading the MNIST dataset in Keras
  • Baseline Model with Multilayer Perceptrons
  • Simple Convolutional Neural Network for MNIST
  • Larger Convolutional Neural Network for MNIST
  • Improve Model Performance With Image Augmentation
  • Keras Image Augmentation API
  • Point of Comparison for Image Augmentation
  • Feature Standardization
  • ZCA Whitening
  • Random Rotations
  • Random Shifts
  • Random Flips
  • Saving Augmented Images to File
  • Project Object Recognition in Photographs
  • Overview of Photograph Object Recognition Dataset
  • Loading The CIFAR-10 Dataset in Keras
  • Simple CNN for CIFAR-10
  • Larger CNN for CIFAR-10
  • Extensions To Improve Model Performance
  • Project: Predict Sentiment From Movie Reviews
  • Movie Review Sentiment Classification Dataset
  • Load the IMDB Dataset With Keras
  • Word Embeddings
  • Simple Multilayer Perceptron Model
  • One-Dimensional Convolutional Neural Network
Download Course Outline