Live AI/ML Sessions | Outside College & Office Hours | Session Recordings on LMS | Learn Around Your Schedule | Built for Students & Working Professionals
Live AI/ML Sessions | Outside College & Office Hours | Session Recordings on LMS | Learn Around Your Schedule | Built for Students & Working Professionals

cloudsandai

Machine Learning & Deep Learning Courses

Three core academic areas taught through integrated Python, scientific computing, experimentation and machine learning implementation.

Courses

Choose Your Learning Path

Two structured programs. One foundations-first approach.

FOUNDATION TRACK

Introduction to Machine Learning

Need details?

Book a Consultation

A structured Machine Learning course where mathematics, statistics and machine learning develop through Python, scientific computing and implementation.

3 Core Areas + 8 Integrated Programming Sessions
120 hrs · 60 lectures
01
Mathematical Foundations for Machine LearningMathematics required to understand how machine learning works.
02
Introduction to Statistical MethodsProbability, statistics, distributions, estimation and hypothesis testing for ML.
03
Machine LearningCore algorithms, intuition, implementation, evaluation and experimentation.
Sessions
8 Integrated Programming Sessions
Total: 8 Sessions
Book a ConsultationView Curriculum
Includes Course 1
COMPLETE TRACK

Machine Learning + Deep Neural Networks

Need details?

Book a Consultation

Includes everything in Course 1, then extends into Deep Neural Networks and advanced deep learning with 6 additional implementation sessions.

3 Core Areas + Deep Learning Extension
180 hrs · 90 lectures(60 + 30 lectures)
01
Mathematical Foundations for Machine LearningMathematics required to understand how machine learning works.
02
Introduction to Statistical MethodsProbability, statistics, distributions, estimation and hypothesis testing for ML.
03
Machine LearningCore algorithms, intuition, implementation, evaluation and experimentation.
Sessions
8 Integrated Programming Sessions
6 Additional Deep Learning Implementation Sessions
Total: 14 Sessions
Book a ConsultationView Curriculum

Comparison

Compare the Courses

FeatureCourse 1FoundationCourse 2Complete
Core academic areas34
Integrated programming sessions88
Deep Neural Networks
Additional deep learning implementation sessions
6
Total programming & implementation sessions814
Duration120 hrs180 hrs (additional 60 hrs)
Lectures6090 (additional 30 lectures)

Course 2 includes the complete Course 1 curriculum.

Curriculum

The Curriculum

Three academic areas form the course structure. Programming and implementation are integrated throughout both courses.

Module 01
01

Mathematical Foundations for Machine Learning

A

Solution of Linear Systems

  • Systems of linear equations
  • Matrices
  • Solving systems of linear equations
B

Vector Spaces

  • Linear independence
  • Basis
  • Rank
C

Analytic Geometry

  • Norms
  • Inner products
  • Lengths and distances
  • Angles and orthogonality
  • Orthonormal basis
D

Matrix Decomposition

  • Determinant and trace
  • Eigenvalues and eigenvectors
  • Cholesky decomposition
  • Eigen decomposition
  • Diagonalization
  • Singular Value Decomposition
  • Matrix approximation
E

Vector Calculus

  • Differentiation of univariate functions
  • Partial differentiation
  • Gradients
  • Gradients of vector-valued functions
  • Gradients of matrices
  • Useful identities for computing gradients
  • Back propagation
  • Automatic differentiation
  • Higher-order derivatives
  • Linearization
  • Multivariate Taylor series
F

Optimization

  • Gradient descent
  • Constrained optimization
  • Lagrange multipliers
  • Convex optimization
  • Learning rate decay
  • Initialization
  • Stochastic gradient descent
  • Hyperparameter tuning
  • Feature preprocessing
  • Local optima
  • Flat regions
  • Differential curvature
  • Momentum
  • AdaGrad
  • RMSProp
  • Adam
G

Dimensionality Reduction and PCA

  • Problem setting
  • Maximum variance perspective
  • Projection perspective
  • Eigenvector computation
  • Low-rank approximation
  • PCA in high dimensions
  • Key steps of PCA
  • Latent variable perspective
H

SVM Mathematical Foundations

  • Mathematical preliminaries for SVM
  • Karush-Kuhn-Tucker conditions
  • Primal/dual perspective
  • Linear SVM
  • Nonlinear SVM
  • Kernels
Module 02
02

Introduction to Statistical Methods

A

Basic Probability & Statistics

  • Measures of central tendency
  • Measures of variability
  • Basic probability concepts
  • Axioms of probability
  • Mutually exclusive events
  • Independent events
B

Conditional Probability & Bayes Theorem

  • Conditional probability
  • Independent events
  • Total probability
  • Bayes theorem
  • Introduction to Naïve Bayes
C

Probability Distributions

  • Random variables
  • Discrete and continuous random variables
  • Expectation
  • Mean
  • Variance
  • Covariance
  • Joint distributions
  • Transformation of random variables
  • Bernoulli distribution
  • Binomial distribution
  • Poisson distribution
  • Normal/Gaussian distribution
  • t-distribution
  • F-distribution
  • Chi-square distribution
D

Hypothesis Testing

  • Random sampling
  • Stratified sampling
  • Sampling distributions
  • Central Limit Theorem
  • Interval estimation
  • Confidence level
  • Testing of hypothesis
  • Mean-related models
  • Proportion-related models
  • ANOVA — single factor
  • ANOVA — dual factor
  • Maximum likelihood
E

Prediction & Forecasting

  • Correlation
  • Regression
  • Time series analysis
  • Components of time series data
  • Moving averages
  • Weighted moving averages
  • AR
  • ARMA
  • ARIMA
  • SARIMA
  • SARIMAX
  • VAR
  • VARMAX
  • Simple exponential smoothing
F

Gaussian Mixture Models & Expectation Maximization

  • Gaussian Mixture Model
  • Expectation Maximization
Module 03
03

Machine Learning

A

Introduction

  • Introduction to Machine Learning
  • Types / taxonomy of Machine Learning
  • Design a learning system
  • Challenges in Machine Learning
B

Machine Learning Workflow

  • Role of data
  • Data preprocessing
  • Data wrangling
  • Data skewness removal / sampling
  • Model training
  • Model testing
  • Performance metrics
C

Linear Models for Regression

  • Direct solution method
  • Gradient descent
  • Batch gradient descent
  • Stochastic gradient descent
  • Mini-batch gradient descent
  • Linear basis function models
  • Bias-variance decomposition
D

Linear Models for Classification

  • Discriminant functions
  • Decision theory
  • Probabilistic discriminative classifiers
  • Logistic regression
  • Log-loss function
  • Gradient descent
  • Multi-class classification
E

Decision Trees

  • Information theory
  • Entropy
  • Entropy-based decision tree construction
  • Avoiding overfitting
  • Minimum Description Length
  • Continuous-valued attributes
  • Missing attributes
F

Instance-Based Learning

  • k-Nearest Neighbor
  • Locally Weighted Regression
  • Radial Basis Functions
G

Support Vector Machines

  • Linearly separable data
  • Non-linearly separable data
  • Kernel Trick
  • Mercer kernels
  • Applications to structured data
  • Applications to unstructured data
H

Bayesian Learning

  • MLE hypothesis
  • MAP hypothesis
  • Bayes rule
  • Optimal Bayes classifier
  • Naïve Bayes classifier
  • Probabilistic generative classifiers
  • Bayesian interpretation of linear regression
I

Ensemble Learning

  • Combining classifiers
  • Bagging
  • Random Forest
  • Boosting
  • AdaBoost
  • Gradient Boosting
  • XGBoost
J

Unsupervised Learning

  • K-Means clustering
  • K-Means variants
  • Mixture models for probabilistic clustering
  • Expectation Maximization review
  • Applications
K

ML Model Evaluation

  • Comparing Machine Learning models
  • Bias
  • Fairness
  • Interpretability

Learning Methodology

Integrated Programming & Implementation

Programming runs alongside the academic curriculum rather than being treated as a separate subject. Every major concept is connected to computation, coding, experimentation, visualization, and algorithm implementation.

Learn the concept → Code it → Experiment with it → Understand it

Theory ↔ Computation ↔ Implementation, throughout the curriculum

01Mathematics
02Code & Compute
03Experiment
04Machine Learning

This is a recurring learning cycle, not a sequence completed before coding begins.

PythonNumPyPandasMatplotlibScientific ComputingAlgorithm ImplementationData AnalysisML ImplementationProblem SolvingExperiments and Visualization

Explore integrated programming topics

A

Python Foundations

  • Python syntax
  • Variables and data types
  • Conditionals
  • Loops
  • Functions
  • Modules
  • Basic debugging
B

Programming Fundamentals

  • Problem decomposition
  • Functions
  • Recursion
  • Computational thinking
  • Code organization
  • Basic complexity concepts
C

Data Structures

  • Lists
  • Tuples
  • Dictionaries
  • Sets
  • Stacks
  • Queues
  • Practical use of data structures
D

Algorithms

  • Searching
  • Sorting
  • Recursion
  • Algorithmic thinking
  • Big-O / computational complexity
  • Implementation-oriented problem solving
E

NumPy & Numerical Computing

  • Arrays
  • Vectorization
  • Broadcasting
  • Matrix operations
  • Numerical computation
F

Scientific Computing

  • Numerical differentiation
  • Numerical integration
  • Simulation
  • Numerical optimization
  • Computational experiments
G

Data Handling & Visualization

  • Pandas
  • Data cleaning
  • Exploratory data analysis
  • Matplotlib
  • Visualization
H

Machine Learning Programming

  • Translating mathematical equations into code
  • Implementing ML algorithms
  • Training workflows
  • Evaluation
  • Computational experiments

Course 1

8 Integrated Programming Sessions

Course 1 includes 8 coding and implementation sessions that run alongside the academic curriculum, connecting concepts with Python, scientific computing and experiments.

Python
Coding
Implementation
Problem Solving
ML-oriented Programming
8Programming
Sessions

Course 2

6 Additional Deep Learning Sessions

Course 2 includes Course 1's 8 integrated programming sessions, plus 6 additional deep-learning implementation sessions. Implementation continues throughout the advanced topics.

14Programming
Sessions
8Integrated programming sessions
+
6Deep Learning Implementation

Course 2 Extension

Deep Neural Networks

Progress from classical machine learning into modern deep learning.

Included in Course 2
C2

Deep Neural Networks

01

Fundamentals of Neural Networks

  • Supervised learning
  • Unsupervised learning
  • Semi-supervised learning
  • Reinforcement learning
  • Why Deep Learning?
  • Applications of Deep Learning
  • Biological neuron vs artificial neuron
  • Connectionism model
  • Perceptron
  • Perceptron learning algorithm
  • XOR problem
  • Multilayer Perceptron
  • MLP as classifiers
  • Universal approximators
  • Depth and width
02

Deep Feedforward Neural Networks

  • Forward propagation
  • Backward propagation
  • Training DNNs using Gradient Descent
  • Computational graphs
  • Activation functions
  • Softmax regression
  • Impact of depth in DNN
03

Optimization of Deep Models

  • Saddle points
  • Plateau
  • Non-convex optimization intuition
  • Optimization algorithms
  • Momentum-based algorithms
  • Adaptive learning-rate algorithms
04

Regularization for Deep Models

  • Model selection
  • Underfitting
  • Overfitting
  • L1 regularization
  • L2 regularization
  • Dropout
  • Vanishing gradients
  • Exploding gradients
  • Covariate shift
  • Parameter initialization
  • Batch normalization
05

Convolutional Networks

  • Convolutions for images
  • Learning a kernel
  • Padding
  • Stride
  • Channels
  • Pooling
  • Designing CNNs
  • Popular CNN architectures
  • Transfer learning
  • Applications of CNNs
06

Sequence Models

  • Recurrent Neural Networks
  • Backpropagation Through Time
  • Exploding gradients
  • Vanishing gradients
  • Gates
  • Popular RNN architectures
  • Applications of RNNs
  • GRU
  • LSTM
  • BiLSTM
07

Attention Mechanism

  • Attention pooling
  • Attention scoring functions
  • Multi-head attention
  • Self-attention
  • Positional encoding
  • Transformer architecture
  • Applications of Transformers
08

Neural Network Search

  • Search space
  • Search algorithms
  • Evaluation strategy
09

Time Series Modelling and Forecasting

  • Univariate CNN models
  • Multivariate CNN models
  • Multi-step CNN models
  • Univariate LSTM models
  • Multivariate LSTM models
  • Multi-step LSTM models
10

Other Learning Techniques

  • Federated learning
  • Meta learning
  • Online / incremental learning
01

Fundamentals

02

Feedforward Networks

03

Optimization

04

Regularization

05

CNNs

06

Sequence Models

07

Attention

08

Transformers

09

Neural Network Search

10

Time Series Forecasting

Enquire About Course 2Back to Courses

Course Selection

Which Track Is Right For You?

Course 1Call to know more

Foundation Track

Build a foundation in mathematics, statistics and machine learning, with Python for Machine Learning and implementation integrated throughout.

3 Core Areas
120 hrs · 60 lectures
8 Integrated Programming Sessions
Theory ↔ Computation ↔ Implementation
Call to know more
Course 2Call to know more

Machine Learning + Deep Neural Networks

Includes everything from Course 1, then extends into Deep Neural Networks, CNNs, Sequence Models, Attention, Transformers and advanced deep learning. Implementation continues throughout these topics.

Everything in Course 1
Deep Neural Networks, CNNs and Sequence Models
Attention, Transformers and Advanced Deep Learning
180 hrs · 90 lectures (60 + 30 lectures)
8 integrated programming + 6 additional deep-learning implementation sessions

Course 2 includes everything in Course 1.

Call to know more

Start Learning

Build the Foundations.
Then Go Deeper.

Learn theory and computation together, then continue into deep neural networks with Course 2.

Explore CoursesContact Deven