AI - Full Stack
Ai Full
Stack Training
Machine Learning Data Science
& their importance
Machine Learning
Data Science &
Their Importance
1. Big Data
2. Data Mining
3. Cloud Computing
4. Machine Learning
5. Business Intelligence
6. Artificial Intelligence
7. DataWarehousingo Data Visualization
8. KeyElementsofMachineLearning
&Data Science& differences
betweenthem
Introduction To
Machine Learning
What is Machine Learning (ML)?
• How machineslearn
Types of learning: Supervised, Semi-supervised,
Unsupervised, Reinforcement.
• BasicsofClassification,Regressionand
Clusteringalgorithms
• Creating your first Prediction Model
• Training & Model Evaluation
• Choosing Machine Learning Algorithm
Python
Language
* Operators, Operands andExpressions
* Python Data Types
* Conditional statements in Python
* Loops in Python
* Lists anddictionaries and Tuples
* Programming practice in Python
* Iterators & Generators
* File Handling in Python
* Modules and Libraries
* Classes and Objects
* String Formatting in Python
* Decorators, Context Managers, Regular Expressions
* List and DictionaryComprehensions
* Lambda and Argument Passing
* Multiple Inheritance
Probability And
STATISTICS
LinearAlgebra (Vectors,Matrix, Eigen Values)
Probability andStatistics
Hypothesis testing
Optimization
GETTING STARTED WITH NUMPY, PANDAS,
Matplotlib, Sk-learn, seaborn
> Introduction to Numpy
> Arrays, Matrices,
> Various operations on arrays and matrices
> Introduction to Pandas
> Reading csv and matlabfiles
> Data frame object manipulation in python
> Various operations on dataframe
> Visualization using Matplotlib
> Scatter plots, line plots etc on a givendata
> Advance visualization usingSeaborn
> Histograms, heatmaps, box plots etc using seaborn
Advanced Machine Learning Algorithms
Supervised Machine Learning algorithms
Linear Regression
Multi Feature
Logistic Regression
2 Class and Multi class
Decision/Classification Trees
EnsembleModels
* K-Nearest Neighbours (KNN)
* Naive Bayes
* Introduction to Neural Network (DeepLearning)
• Feed Forward Neural Network
• Forward Propagation
• Backward Propagation
* Support VectorMachine
• Unsupervised Machine Learning algorithms Clustering
with K-means Clustering
• Bias-Variance Tradeof
• Regularization
• Parametertuning & grid search optimization
• Time Series Analysis
Projects with Machine Learning
Email spam detection problem with preprocessed Email Data
Image compression Problem
Flower species classification problem
Titanic Survivor classification problem from kaggle
Fifa ranking dataset from kaggle
Profit Prediction Problem
Business Case of whether a chip will be accepted or not
Business case of clustering from dataset
Wine classification dataset and problem from Kaggle
Variety of Problems from Kaggle Competition Data Sets
Data Science
Basic Functionalities of a data object
Merging of Data objects
Concatenation of data objects
Types of Joins on dataobjects
Exploring aDataset
Analysing adataset
Pandas Function-Ndim(), axes(), values(), head(),
tail(), sum(), std(), iteritems(), iterrows(), itertuples()
GroupBy operations
Aggregation
Concatenation
Merging
Joining
Data Collection &Preparation
Data Mugging
Outlier Analysis
Missing value treatment
FeatureEngineering
Data Transformation
Normalization vs Standardization
Creating Dummies
Dimensionality Reduction
Principal ComponentAnalysis
Data Potting andVisualization
Data Aggregation and Group Operations
Data Wrangling: Join, Combine and Reshape
Probability
Understand rules of probability
Learn about dependent and independent events
Discuss probability distribution
Explain Central Limit Theorem
Statistics For Machine Learning And Data Science
⦁ Point Estimation ⦁ Experimental Designing
⦁ Confidence Margin ⦁ Confidence Interval
⦁ Hypothesis Testing ⦁ Student’s t distribution
⦁ Levels of Hypothesis Testing ⦁ Binomial Distribution
⦁ Anova ⦁ A/B Testing
⦁ Co-Relation ⦁ Hypothesis Testing
⦁ Parametric Test ⦁ t-Tests
⦁ Parametric Test Types ⦁ ANOVA
⦁ Non- Parametric Test ⦁ Chi-square test
⦁ PCA ⦁ KNN
⦁ Categorical Variables ⦁ R Square
Data Clustering
Association and Dependence
Causation and Correlation
Covariance
Simpson’s Paradox
Clustering Techniques
Regression Modelling
⦁
Linear & Logistic and Regression Techniques
⦁
Problem of Collinearity
⦁
WOE and IV
⦁
Residual Analysis
⦁
Heteroscedasticity
⦁
Homoscedasticity
Projects with Data Science
* Every Project Done in Machine Learning
with Advance Analysis
* HousePricePredictionin Kaggle with Statistical
Model and Machine Learning
* Credit Card Fraud Detection using Advance Analytics
* Kidney Disease detection using Data Analytics in Kaggle
Deep Learning
Introduction to DeepLearning
Introduction to DeepLearning
Necessity of Deep Learning over Machine Learning
History and evolution of various deep learning algorithms
AI and how is Deep Learning one ofthe paths to AI in
the recent era
Types of Machine Learning and Deep Learning
Why Deep Learning
Master Deep Network
o Layered structures o Working of a DeepNetwork
o Types of layers o What is Perceptron
o Forward pass o What isNeuron
o Back propagation - o Sigmoidneuron
chain rule o Activation functions
andevaluationmetrics o Cost function
o Gradient Descent o Optimization
o SGD (for a SoftMax o Dense networks
classifier example) o Regularization
o Nestorov's momentum
o RMS Prop
o Adam
Objective on Neural networks using TensorFlow
⦁ Introduction to TensorFlow
⦁ Advantages of TensorFlow
⦁ Vectorization
⦁ Variable declaration
⦁ Session
⦁ Graphs Lecture
⦁ Tensorboard
⦁ Implementation of a simple Perceptron in TensorFlow
⦁ Implementing a simple feed forward Neural Network
in TensorFlow
⦁ Various activation functions and their ranges
⦁ Pros and cons of Activation functions
⦁ Why to use specific activation function
⦁ When is the usage of activation function
⦁ What are the ones used in industry for specific tasks
⦁ Visualization of competition based craft and model results
Deep Learning Packages/APIs
⦁ PyTorch
⦁ Creating and Deploying Neural Networks
⦁ using Keras and Tensorflow
⦁ Dialogue Flow
⦁ Alexa Skills
⦁ Building a model of object detection
Computer Vision
⦁ Introduction to OpenCV
⦁ Image Preprocessing
⦁ Image classification using CNNs
Natural Language Processing (NLP)
Introduction to NLTK Named Entity Recognition
Converting Text tofeatures One Hot Encoding
Tokenization Count Vectorizer
Frequency Distribution N-grams
Different Types of Tokenizers Co-occurrence matrix
Bigrams, Trigrams & Ngrams Hash Vectorizer
Stemming TF-IDF
Lemmatization Word Embedding
Stopwords Implementing Fast Text
POS Tagging
Analyzing Sentence Structure
⦁ Syntax Trees
⦁ Chunking
⦁ Chinking
⦁ Context Free Grammars (CFG)
⦁ Automating Text Paraphrasing
Text Classification
⦁ Bag of Words
⦁ CountVectorizer
⦁ Term Frequency (TF)
⦁ Inverse Document Frequency (IDF)
⦁ Converting text to features and labels
⦁ Naive Bayes Classifier
⦁ SVM Classifier
⦁ Topic Modeling using LDA
⦁ NN Classifier
⦁ Leveraging Confusion Matrix
Text to Speech and Speech to Text
Advance NLP
Industry Use cases discussion and problem solving
Deep Learning in NLP
Information retrieval
Text Classification – CNN, RNN, LSTM
Predicting next words/sequence of words
using LSTM for emails
Projects on Deep Learning
Creating a Rule BasedChatbot
Creating a conversationalChatbot
Analysing Text datasets fromKaggle
Amazon Reviews SentimentalAnalysis
Monitory Instruments reviews and feedbacks data
Handwritten Digit RecognitionProblem
Pre Processing Email data and detecting spam problem
Recommender System
Learn from Industry Experts, Advance
Your Career and Be in Demand
Top Machine Learning,
AI, Blockchain, React
JS Training in Bangalore
Who We Are?
NearLearn™ is an Ed-tech brand registered under the
company NEAR AND LEARN PRIVATE LIMITED. We offer
specialization courses in Machine learning, Data Science,
Artificial Intelligence, Python, Big Data, Blockchain,
Reactjs and React Native, Migrating Application to Aws
Training, Aws SysOps Administrator in Bangalore. Here
Mission & Vision
you will get Classroom Training and Online Training.
We aim to help Freshers, Corporate, Software Engineers, Our mission is to provide the best standard programs through which
Individuals to get knowledge into their minds through their dream can come true, and they would be able to achieve their aim
in the way they want. Our resources and reputed trainers are committed
their hands-on projects and realtime training.
to taking their trainees to a high level. NearLearn's graduated students
are build to take every challenge in the job market.
Career and Placement Support
Get Hired Classroom Training
Interview scheduling Online Training
Hands-on Projects Corporate Training
Resume Structure Self-Placed Training
CONTACT US FOR MORE
+91-80-41700110 [email protected] Near And Learn Pvt. Ltd. No: 61,1st Floor, 7th Main,
www.nearlearn.com 12th Cross Rd, BTM 2nd Stage Bangalore – 560 076
