Professional AI With Data Science Course

Module 1

1. A-Z Python for data science Installation of python IDE’S
2. Python environment Setup.
3. Python data types: List, Tuple Set, Dictionary
4. Conditional statements
a. If
b. if-else.
c. Nested if
d. if elif ladder
5. Loops
a. for loop,
b. while loop
6. Functions
a. Custom functions
b. Inbuilt function.
7. OOP Concept
a. Class & object
b. Inheritance
c. Init method
8. Exception handling
a. Try
b. Except
c. Finally
d. Types of exceptions
9. File handling
a. Read
b. Write
c. Append

Module 2 – Statistics

1. Definition
2. inferential and descriptive statistics
3. Mean, median, mode
4. Variant, standard deviation, range, skewness, kurtosis, untitance and interval, z-distribution, tardancy, p-value, f-test, anova, chi-square test and masseuse of dispersion

Module 3 – Probability

1. Definition, types of probability (conditional probability, joint probability)
2. Random variables, probability distribution, bayer’s theorem
3. Linear algebra, eigen vectors & eigen values, maximize & minimize functions. Iift ratio, orthogonal matrix
4. Central limit theorem, hypothesis testing, power law
5. Correlation regression & covariance
6. Probability mass function, cumulative distribution function.

Module 4 – Numpy

1. Installation & introduction of NumPy package
2. NumPy basics
3. Creation of NumPy arrays
4. Array operations
5. Array slicing
6. Multidimensional array
7. Python list VS NumPy arrays
8. Basic linear algebra operations

Module 4 – Pandas

1. Installation and introduction of pandas package
2. Pandas basics
3. Indexing and Recording files
4. Data operations
5. Grouping, merging, joining & concatenating
6. Creating objects
7. Viewing data
8. Data selection
9. Data manipulation
10. Working with data & time
11. Working with different types of files ( CSV, Excel, Text file etc.)

Module 5 – Data Visualisation

1. Basics of visualisation
2. Installation of visualisation packages like matplotlib, seaborn etc.
3. Working with different types of plot / grapes
a. Scatter
b. Line chart
c. Bar chart
d. Histogram
e. Boxplot
f. a-a plot
g. Pie-chart etc

Module 6 – Data preparation / data cleaning / munging / wrangling

1. Outlier analysis / treatment
2. Missing value imputation
3. Data filtering
4. Typecasting
5. Transformations
6. Duplicate data handling
7. Categorical data handling
8. Discretization
9. Standardisation and normalisation of data
10. Zero & near zero variance features

Module 7 – Feature Engineering

1. Rounding
2. Binarization
3. Binning
4. Transformations
5. Feature engineering on text data
6. Feature scaling
7. Feature selection techniques

Module 1:-Basics

• Database Concepts
• E-R Modeling and Diagram
• Normalization
• SQL Server
• Introduction to SQL
• DDL and DML Statements
Module 2: Queries (DQL)
• Select Statement
• Top, Distinct, Null etc…Keywords
• String and Arithmetic Expressions
• Where Clause with Operators
• Sorting data using Order By clause, basic of Sub Queries
Module 3: Aggregate Functions
• functions in Queries
• predefined functions
• Group By with Rollup and Cube and Group By with Rollup and Cube
• Count, Sum, Min, Max, Avg Group By and Having Clause
Module 9: Joins and Set – Operations
• Introduction to Joins Cross Joins
• Inner Join, Outer Join, Self-Join
• Unions, Intersect and Except
• Implementation of Data integrity
Module 5: Constraints
• Unique
• Not NULL
• Primary Key
• Default Check Foreign Key
Module 6: Implementing Views
• Introduction & Advantages of Views
• Creating, Altering, Dropping Views, SQL Server Catalogue Views
Module 7: Extra – Features
• Pivot Table
• Common Table Expression
• Ranking Functions Using BLOB data type
• Using XML data type

Module 1 – Statistics

1. Definition
2. inferential and descriptive statistics
3. Mean, median, mode
4. Variant, standard deviation, range, skewness, kurtosis, untitance and interval, z-distribution, tardancy, p-value, f-test, anova, chi-square test and masseuse of dispersion

Module 2- Probability

1. Definition, types of probability (conditional probability, joint probability)
2. Random variables, probability distribution, bayer’s theorem
3. Linear algebra, eigen vectors & eigen values, maximize & minimize functions. Iift ratio, orthogonal matrix
4. Central limit theorem, hypothesis testing, power law
5. Correlation regression & covariance
6. Probability mass function, cumulative distribution function.

Module 1 – Numpy

1. Installation & introduction of NumPy package
2. NumPy basics
3. Creation of NumPy arrays
4. Array operations
5. Array slicing
6. Multidimensional array
7. Python list VS NumPy arrays
8. Basic linear algebra operations

Module 2 – Pandas

1. Installation and introduction of pandas package
2. Pandas basics
3. Indexing and Recording files
4. Data operations
5. Grouping, merging, joining & concatenating
6. Creating objects
7. Viewing data
8. Data selection
9. Data manipulation
10. Working with data & time
11. Working with different types of files ( CSV, Excel, Text file etc.)

Module 3 – Data Visualisation

1. Basics of visualisation
2. Installation of visualisation packages like matplotlib, seaborn etc.
3. Working with different types of plot / grapes
a. Scatter
b. Line chart
c. Bar chart
d. Histogram
e. Boxplot
f. a-a plot
g. Pie-chart etc

Module 4 – Data preparation / data cleaning / munging / wrangling

1. Outlier analysis / treatment2. Missing value imputation
3. Data filtering
4. Typecasting
5. Transformations
6. Duplicate data handling
7. Categorical data handling
8. Discretization
9. Standardisation and normalisation of data
10. Zero & near zero variance features
Module 9 – Feature Engineering
1. Rounding
2. Binarization
3. Binning
4. Transformations
5. Feature engineering on text data
6. Feature scaling
7. Feature selection techniques

Module 5 – machine learning algorithm

1. ML introduction
2. ML VS AI
3. AI VS ML VS DL
4. Different types of ML algorithm ( unsupervised & supervised )
Module 11 – Unsupervised learning
1. clustering
a. Hierarchical clustering
b. DB-Scan clustering
2. Dimension reduction
a. PCA
b. LDA
c. SVD
3. Association rule
a. Market basket analysis
b. Measure of association
c. Apriori algorithm

Module 6 – Supervised algorithm / regression

1. Regression analysis / SLR
a. Scatter diagram
b. Correlation causation
c. Correlation coefficient
d. Simple linear regression
2. Non-linear regression techniques
3. Model evaluation
a. Loss function
b. Cost function
c. Eraser function
4. Multiple linear regression
a. SLR VS MLR
b. Line assumption
c. Residuals and predicting variable plots
d. Influence plot
e. Feature selection
5. Lasso – ridge regression
a. Regularisation techniques
b. Over fitting and underfitting
c. Elastic net regression
6. Logistic regression
a. Confusion matrix
b. Performance matrix
c. ROC curve
d. AVC curve
7. Multi class regression
a. Multinomial regression
b. Ordinal logistic regression

Module 7- machine learning algorithms / classifications

1. KNN classification
a. Parametric learning
b. Bias variance frecte
c. K value
2. Decision tree
a. Elements of Decision tree
b. Greedy algorithm
c. Measure of entropy
d. Gini index, gain ratio
e. Information gain
f. Pruning technique
3. Ensemble techniques
a. Bagging & boosting
i. Voting
ii. Stacking
iii. Bootstrap aggregation
iv. Random forest IC fold validation
b. Adaboost & extreme gradient boosting
i. Adaptive boosting
ii. Reweighting
iii. Hyperparameter
iv. Cross validation
v. K fold CV
4. Naive bayes
a. Conditional probability
b. Naive – bayes classifier / Probabilistic classification
c. Prior probability
i. Data prior
ii. Class prior
iii. Marginal likelihood
d. Posterior probability
e. Text classification using naive bayes
Module 14 – Recommendation Engine
1. User based collaborative filtering
2. Content based filtering
3. SVD in recommendation

Module 1 – Text mining & natural language processing

1. Bag of words
2. Pre-processing
3. DTM & TDM
4. Stemming
5. Lemmatization
6. TF / TF – IDF
7. Word cloud
8. Corpus level word clouds
a. Sentimental analysis
b. Positive word clouds
c. Negative word cloud
d. Unigram, bigram, trigram
9. Latent Dirichlet Allocation (LDA)
10. Topic modelling
11. Parts of speech tagging
Module 16 – Network analytics
1. Definition of a network / graph
2. Vertices / nocks
3. Edges / connection / links
a. Adjacency matrix
b. Unidirectional
c. Bidirectional
4. Node properties
5. Network properties

Module 1 – time series / forecasting

1. Survival analytics
a. Duration analysis
b. Censoring
c. Survival, hazard, cumulative hazard functions
d. Kaplon – mier survival functional and curve
2. Introduction to time series
3. Steps to forecasting
4. Lagplot & ACF
5. Different errors in forecasting
6. Model based approaches
7. AR model for eraser
8. Data driven algorithms
9. ARIMA ( auto – registration integrated moving average )
10. Smoothing techniques

Module 1 – Deep learning basics

• Introduction to Biological & Artificial Neuron
• Mathematical foundation-DL
• Introduction to ANN,CNN and RNN
• Neuron, Weights, Activation function, Integration function, Bias and Output
• Introduction to Perceptron
• Multi-Layered Perceptron (MLP)
• Activation functions
1. Identity Function,
2. Step Function,
3. Ramp Function,
4. Sigmoid Function,
5. Tanh Function,
6. ReLU, ELU, Leaky ReLU & Maxout
• Back Propagation
• Weights Calculation in Back Propagation
Module 19 – ANN
• Error Surface, Learning Rate & Random Weight Initialization
• Local Minima in Gradient Descent Learning
• Gradient Primer, Activation Function, Error Function, Vanishing Gradient, Error Surface challenges, Learning Rate challenges, Decay Parameter, Gradient Descent Algorithmic Approaches, Momentum, Nestrov Momentum, Adam, Adagrad, Adadelta & RMSprop
• Overfitting, DropOut, DropConnect, Noise, Data Augmentation, Parameter Choices, Weights Initialization (Xavier, etc.)

Module 2 – CNN

• Parameters used in MLPs
• Convolution Networks
• Convolution Layers with Filters
• Pooling Layer, Padding, Stride
• Transfer Learning
• Weight decay, Drop Connect, Data Manipulation Techniques & Batch Normalization

Module 3- RNN

• Introduction to Adversaries
• Language Models – Next Word Prediction, Spell Checkers, Mobile Auto-Correction, Speech Recognition & Machine Translation
• Traditional Language model
• Disadvantages of MLP
• Introduction to State & RNN cell
• Introduction to RNN
• RNN language Models
• Back Propagation Through time
• RNN Loss Computation
• Types of RNN
• Combining CNN and RNN for Image Captioning
• Architecture of CNN and RNN for Image Captioning
• Bidirectional RNN and Deep Bidirectional RNN
• Disadvantages of RNN
• Frequency-based Word Vectors
• Count Vectorization (Bag-of-Words, BoW), TF-IDF Vectorization
• Word Embeddings
• Word2Vec – CBOW & Skip-Gram
• FastText, GloVe

Module 4 – Computer Vision

• Introduction to Vision
• Importance of Image Processing
• Interclass Variation, ViewPoint Variation, Illumination, Background Clutter, Occlusion & Number of Large Categories
• Image Transformation, Image Processing Operations & Simple Point Operations
• Image Filtering
• Introduction to Convolution
• Boundary Effects
• Image Sharpening
• Template Matching
• Edge Detection – Image filtering, Origin of Edges, Edges in images as Functions, Sobel Edge Detector
• Effect of Noise
• Laplacian Filter
• Smoothing with Gaussian
• LOG Filter – Blob Detection
• Noise – Reduction using Salt & Pepper Noise using Gaussian Filter
• Nonlinear Filters
• Bilateral Filters
• Canny Edge Detector – Non Maximum Suppression, Hysteresis Thresholding
• Image Sampling & Interpolation – Image Sub Sampling, Image Aliasing, Nyquist Limit, Wagon Wheel Effect, Down Sampling with Gaussian Filter, Image Pyramid, Image Up Sampling
• Image Interpolation – Nearest Neighbour Interpolation, Linear Interpolation, Bilinear Interpolation & Cubic Interpolation
• Introduction to the dnn module
o Deep Learning Deployment Toolkit
o Use of DLDT with OpenCV4.0
• OpenVINO Toolkit
o Introduction
o Model Optimization of pre-trained models
o Inference Engine and Deployment process

Module 5 – LSTM AND GRUs

• Introduction to LSTM – Architecture
• Importance of Cell State, Input Gate, Output Gate, Forget Gate, Sigmoid and Tanh
• Mathematical Calculations to Process Data in LSTM
• RNN vs LSTM – Bidirectional vs Deep Bidirectional RNN
• Deep RNN vs Deep LSTM
Module 24 – Transformers,BERT,GPT3
• Seq2Seq (Encoder – Decoder Model using RNN variants)
• Attention Mechanism
• Transformers (Encoder – Decoder Model by doing away from RNN variants)
• Bidirectional Encoder Representation from Transformer (BERT)
• OpenAI GPT-2 & GPT-3 Models (Generative Pre-Training)
• Text Summarization with T5
• Configurations of BERT
• Pre-Training the BERT Model
• ALBERT, RoBERTa, ELECTRA, SpanBERT, DistilBERT, TinyBERT

Module 6 – AUTO ENCODERS AND VARIATIONAL AUTOENCODERS, RBM

• Autoencoders
o Intuition
o Comparison with other Encoders (MP3 and JPEG)
o Implementation in Keras
• Deep AutoEncoders
o Intuition
o Implementing DAE in Keras
• Convolutional Autoencoders
o Intuition
o Implementation in Keras
• Variational Autoencoders
o IntuitionImplementation in Keras
• Introduction to Restricted Boltzmann Machines – Energy Function, Schematic implementation, Implementation in TensorFlow

Module 7 – DBNs

• Introduction to DBN
• Architecture of DBN
• Applications of DBN
• DBN in Real World
Module 27 – GAN
• Introduction to Generative Adversarial Networks (GANS)
• Data Analysis and Pre-Processing
• Building Model
• Model Inputs and Hyperparameters
• Model losses
• Implementation of GANs
• Defining the Generator and Discriminator
• Generator Samples from Training
• Model Optimizer
• Discriminator and Generator Losses
• Sampling from the Generator
• Advanced Applications of GANS
o Pix2pixHD
o CycleGAN
o StackGAN++ (Generation of photo-realistic images)
o GANs for 3D data synthesis
o Speech quality enhancement with SEGAN
Module 28 – Super Resolution GAN
• Introduction to SRGAN
• Network Architecture – Generator, Discriminator
• Loss Function – Discriminator Loss & Generator Loss
• Implementation of SRGAN in Keras

Module 8 – Reinforcement Learning and Q Learning

• Reinforcement Learning
• Deep Reinforcement Learning vs Atari Games
• Maximizing Future Rewards
• Policy vs Values Learning
• Balancing Exploration With Exploitation
• Experience Replay, or the Value of Experience
• Q-Learning and Deep Q-Network as a Q-Function
• Improving and Moving Beyond DQN
• Keras Deep Q-Network

Module 9- Speech Recognition

• Speech Recognition Pipeline
• Phonemes
• Pre-Processing
• Acoustic Model
• Deep Learning Models
• Decoding
Module 31 – Automatic Text Recognition and chatbot
• Introduction to Chatbot
• NLP Implementation in Chatbot
• Integrating and implementing Neural Networks Chatbot
• Introduction to Sequence to Sequence models and Attention
o Transformers and it applications
o Transformers language models
 BERT
 Transformer-XL (pretrained model: “transfo-xl-wt103”)
 XLNet
• Building a Retrieval Based Chatbot
• Deploying Chatbot in Various Platforms

• Introduction
• Basic charts in tableau
• Organizing and simplifying Data
• Visual analytics
• Advanced analytics in tableau
• Maps in tableau
• Dashboards
• Stories
• Calculations
• LOD Expressions
• Custom charts

• Setup Excel, Microsoft Excel Startup Screen
• Introduction to the Excel software
• Customizing the Excel Quick Access Toolbar, More on the Excel Interface
• Structure of an Excel Workbook, Saving an Excel Document
• Opening an Existing Excel Document, Common Excel Shortcut Keys
• Entering Text to Create Spreadsheet Titles
• Working with Numeric Data in Excel
• Entering Date Values in Excel, Working with Cell References
• Creating Basic Formulas in Excel
• Relative Versus Absolute Cell References in Formulas
• Understanding the Order of Operation
• The structure of an Excel Function
• SUM() Function, MIN() and MAX() Functions
• AVERAGE() Function, COUNT() Function
• Adjacent Cells Error in Excel Calculations Using the AutoSum Command
• Excel’s AutoSum Shortcut Key
• AutoFill Command to Copy Formulas
• Moving and Copying Data in an Excel Worksheet
• Inserting and Deleting Rows and Columns, Changing the Width and Height of Cells
• Hiding and Unhiding Excel Rows and Columns
• Renaming an Excel Worksheet, Deleting an Excel Worksheet
• Moving and Copying an Excel Worksheet
• Font Formatting Commands and Changing the Background Color of a Cell
• Adding Borders to Cells
• Excel Cell Borders Continued
• Formatting Data as Currency Values
• Formatting Percentages
• Using Excel’s Format Painter
• Creating Styles to Format Data
• Merging and Centering Cells
• Using Conditional Formatting
• Editing Excel Conditional Formatting
Add-

• AIOPS
• Github
• Dockers and Containers
• Auto AI
• Explainable AI
• Kafka
• CICD Pipeline
• MongoDB