Applied Artificial Intelligence 2020-06-29T18:37:06+00:00

Course on

Applied Artificial Intelligence

Applied Artificial Intelligence course is designed for professionals who intend to transition to the role of an AI Expert / Specialist. Applied AI course is for Software developers, Project Managers, Business Analyst, Data Scientist, Data Engineers who wants to build a solid foundation in Artificial Intelligence to understand and implement the tools and techniques that make a system intelligent.

Enrol
Video-Course Description

Key Features

  • Gain experience with handson exercises

  • Instructor led training

  • Flexibility of learning in class or online

  • Industry exposure – Use Cases

  • Learn by doing – Assignments, Tasks

  • Curriculum – par with Industry

  • Innovative Approach – Discussions, Quiz, webinar

  • Project Based Learning Approach

  • Capstone Projects

  • Solutions for your skill gaps

  • Upskilling and Level Setting

  • Dedicating mentoring sessions from industry experts

  • Career Support

  • Industry valued Certificate

Talk to an Expert

Schedule a meet with AI consultant to know more about the course, and the discussion will help to take action over learning.

Schedule a Meet

Schedule – Online (Live) Instructor Led Training

BatchScheduleCourse Fee
Open [One – One]FlexibleINR 180000
USD 2350
Enroll Now
Open [One – Batch ]FlexibleAvail Batch discount by joining as a groupBatch size is limited to 3.

** For payment and instalment options, please contact +91 9841557655 **

Prerequisite :  None

Curriculum

  • Introduction, Installing Python, Anaconda environment
  • Variables , Input Functions
  • Operators, Control Flow
  • String Handling
  • Data Structures-Lists, Tuples, Sets, Dictionary
  • Functions, Modules, Packages
  • File Handling
  • Exception Handling
  • Object Oriented Paradigms
  • Numpy: Introduction, Numerical operations on Numpy
  • Pandas: Getting started with pandas
  • Data Frame Basics, Key Operations on Data Frames
  • Sci-py: working with Scipy
  • Scatter Plot, Line Chart, Histogram
  • Bar Chart, Box plot, Heat Map
  • Pair plot
  • scatter Matrix using Matplotlib
  • Pandas Vizualization
  • Seaborn
  • Working with Different File formats – CSV,JSON, PDF,binary format, HDF5
  • Interacting with data in Sql-Pysql with MysqlDB
  • Interacting with data in Nosql -pymongo with MongoDB
  • HDFS installation
  • HDFS Overview & Data storage
  • Get the data into Hadoop from local machine(Data Loading ) – vice versa
  • Map Reduce model
  • Hive and Pig model
  • Spark installation
  • Spark streaming
  • Pydoop and Pyspark implementation
  • Descriptive Statistics: Measuring central tendancy, Variance
  • Inferential Statistics : Hypothesis Test- P test, t test, z-score, Chi square test, ANOVA
  • Probability Distributions: Gaussian, Poisson, Bernouli, Binomial, Uniform, Exponential
  • Linear Algebra
  • Analytic Geometry
  • Matrix Decompositions
  • Vector Calculus
  • Continuous Optimization
  • Time Series, Down sampling
  • Resampling, Upsampling
  • Time deltas
  • Time series forecasting with ARIMA,
  • Multivariate Time Series
  • Getting Started with Data Mining
  • Affinity analysis
  • Recommender Systems
  • Prediction using Linear Regression
  • Scikit-Learn, Prepossessing
  • Fundamentals of Machine learning
  • Supervised Learning ,Unsupervised Learning
  • Regression,Classification and Clustering Problems
  • Various algorithms involved in machine learning problems
  • Regularization Techniques, Cross Validation, Evaluation Metrics
  • Dimensionality Reduction techniques
  • Market Basket Analysis, Recommender Systems
  • Getting started with TensorFlow
  • Loading and exploring the data
  • Data transformation & Data segmentation
  • Tensor and matrix operations
  • Computational graphs
  • Linear regression, Data pipelines
  • Dataset framework & manipulations
  • Loading data for classifiers, extracting data
  • Loss function, optimization, accuracy
  • Model training using TensorFlow
  • Neural Networks Foundations
  • Fundamentals of deep learning
  • Activation Functions
  • Hidden layers, hidden units
  • Illustrate & Training a Perceptron
  • Important Parameters of Perceptron
  • Various neural networks involved in deep learning
  • Creating a sequence of layers and adding layers in Tensorflow and Keras
  • Deep Learning with MLP, CNN
  • RNN, LSTM
  • Regression networks
  • auto encoders
  • Generative Adversarial Networks and WaveNet
  • Word Embeddings
  • Deep reinforcement learning
  • Q learning
  • Compile model by specifying functions & optimizers
  • Execution of the defined model using Tensor flow & Keras
  • Parameters vs Hyper parameter
  • Hyper parameter tuning
  • Regularization
  • Optimization
  • Policy Gradient Methods
  • Data, Operations on Numpy Arrays (Images)
  • Core Operations on Images
  • Image Acquisition, Image Enhancement
  • Image Restoration
  • Manipulating Exposure and Colour Channels Edges And Lines
  • Image Gradients,
  • Canny Edge Detection
  • Image Pyramids
  • Contours, Histograms
  • Geometrical Transformations of images
  • Morphological Transformations
  • Image Transforms
  • Temple Matching
  • Hough Line, Circle Transform
  • Filtering and Restoration
  • Image Threshold
  • Smoothing Images,
  • Foreground Extraction Using Grabcut
  • Detection of Features and Objects
  • Harris Corner, SIFT, SURF, FAST
  • BRIEF, ORB
  • Segmentation of Objects
  • Object Detection and Recognition
  • CNN
  • VGG
  • Inception
  • ResNET
  • SCikit-image
  • OpenCV
  • N Gram Models
  • Bag of N grams
  • TF-IDF, word2vector
  • Smoothing, Interpolation
  • Clustering and Latent Semantic Analysis
  • Corpus
  • WordNet, Raw Text
  • Sourcing, web scraping
  • Regular expressions and Normalization
  • Tokenization, Stemming
  • Lemmatization  Stopwords
  • Distance between two strings
  • NLTK , Spacy
  • POS tagging and Grammars
  • Context Free Grammars
  • Probabilistic CFG
  • Recursive CFG
  • Chunking, Sentence Parse
  • Dependency grammar
  • Projective Dependency
  • Information Extraction in Text- Classification
  • Named Entity Recognition
  • Creating, inversing and using dictionaries
  • Segmenting sentences using classification
  • NLP pipeline
  • Text similarity problem
  • Resolving anaphora
  • Disambiguating word sense
  • Sentiment analysis
  • Chatbot
  • Classification of emails using deep neural networks after generating TF-IDF
  • IMDB sentiment classification using CNN
  • IMDB sentiment classification using bidirectional LSTM
  • Visualization of high-dimensional words in 2D with neural word vector visualization
  • Solve reinforcement learning problems with a variety of strategies
  • using Python, TensorFlow, NumPy, and OpenAI Gym
  • Creating performant apps for ML models StreamLit &
  • Deploy Machine Learning Models’ dashboard using Joblib, Pickle & StreamLit
  • Deploying Streamlit Application in Heroku cloud- PaaS
  • Capstone Project – 1
  • Capstone Project – 2
  • Capstone Project – 3
  • Capstone Project – 4
  • Capstone Project – 5

Tools Covered

Streamlit tool

FAQ(s)

Instructor-led online training is an interactive mode of training. The trainer and learner(s) log in at the same time and live sessions will be done. NO RECORDED VIDEOS. Trainer will be interacting with learners in all sessions throughout the course/training.

All the modules and topics of this course are delivered through live scheduled sessions by the trainers. NO SELF – PACED VIDEOS.

VYOAM supports learners with its learning manage system, in addition with sharing the required materials, data tales and notes. Also the trainers will help you to get it done with the missed session.

Naïve learners with respect to programming and data science can very much take up this course. This program is designed to impart data science skills from scratch. This course will start from basics of Python programming.

NO PRE REQUISITE. However it is expected to have logical thinking, problem solving skills in addition with commitment.

Our trainers are part of Product Development and Consultancy division of VYOAM. They are highly qualified (PhD holders in Artificial Intelligence), AI Experts with years of relevant industrial experience. Our trainers are good at translating highly technical information in ways that others can understand in order to influence the effective knowledge transfer..

Mentors help the learners to set their target learning goals and discuss how to achieve them. Mentors also answer subject experts; provide feedback on projects, and help the learners to build their portfolio in data science domain.

Yes. Mentorship is integrated part of this course. Learners can interact and career assistance from mentors.

After successful completion of assignments, case studies, capstone projects thereby completion of course, learners will be provided with the certificate.

The fees can be paid in 3 to 4 instalments. For more details about payment options and instalments, please contact +91 9841557655.

Yes. There is a group discount. Group discount is offered when you join as a group (3 members in a group)

VYOAM offers training model that upskill the learner, which in turn makes the learner full competitive to acquire job with their skill sets.

Related Courses