Deep Machine Learning

  • Python-Julia Programming

  • Data visualization

  • Machine Learning

  • Deep Learning

  • CNN-convolutional neural network

  • GAN-generative adversarial network

  • RNN-recurrent neural network

  • ADASadvanced driving assistance system

Modules
+
Exercises
+
Articles
Hrs/Week
Training
40 Hrs

Duration

Deep ML

Certification

Course Objective :

Machine learning is all about combining human intelligence with enormous computational power of computer to solve the problems that matters the most to the society. This course will teach you the end-to-end process of data analysis and DEEP machine learning – neural network on it to create model for prediction. We will also teach you how to extract and identify useful features that best represent your image, sound samples, and data to train DEEP learning model to deploying that model to applications on web and mobile apps, additionally we teach you expert secrets to achieve the performance of 99% accuracy in a limited time. We will also teach you how to extract and identify useful features that best represent.

What Will I Learn?

  • Math for Machine Learning
  • Application development for ML
  • Image and Video Processing
  • Speech Processing
  • NLP-NLU-NLG
  • Data Visualization

Includes:

  • 70 Hrs of Classroom
  • 15+ coding Exercises
  • 7+ Projects
  • 5+ Articles
  • 6 Hrs/Week

Course Structure

  • Statistics – Mean, Median, Mode, standard Deviation and variances,
    co-corelation coefficient, data distribution and plotted inferences
  •  Probability- Sets, Addition and multiplication of probability, exclusive,
    exhaustive, mutually exclusive, Bayes theorem and application,
    probability distribution function, probability and log loss function
  •  Linear and polynomial algebra and Plotting and Graphs Matrix and
    Matrices Discreet Structure
  •  Co-ordinate Geometry- line, curve, circle, parabola etc. 5. Function
    Limits and Continuity
  • APPLIED Calculus- APPLIED Differentiation and Integration,
    differential equation
  • Applied Logarithms
  • for imaging processing and Convolutional neural network
  • Signals and system – signal representation (discreet and continuous
    time function)
  • Digital signal processing – conversion of analogy to digital signal and
    performing different filters over digitise signal to extract information such
    as speech processing
  • Digital Image/audio/video processing – Image encoding-decoding
    and applying different types of filter over images to extract the desired
    results
  • Fuzzy logics basic- Algorithm used for Resolving error and paradox
    when machine learning almost fails.
  •  Pre-Processing on Data set.
  • Learning setup introduction.
  • Practical learning.
  • Supervised learning setup (Practical) Linear Regression and
    Gradient descent
    Practical: Price prediction of Pizza
  • Logistic Regression Generative learning algorithms
    Practical: Image to Text converter for modern billing system
  • Gaussian discriminant analysis
  • Naive Bayes.
  • Decision Tree algorithms
  • Support Vector Machines
  • Support Vector Machine with Kernel Trick
    Practical: Face detection
  • Model selection and feature selection. Evaluating and debugging
    learning algorithms.
  • Clustering. K-means. Dimensionality Reduction Anomaly Detection
    Projects :
    a. Cancer Prediction with limited amount of dataset
    b. Star prediction from NASA Dataset
    c. Financial market analysis
    d. Sentimental analysis
    e. Vehicles counting using open CV
    f. Real-time Audio detection
    g. Image search Crawler with NLP
    h. Anomaly Detection in the field of Cyber Security
    i. Data clustering in BIG DATA
  • Introduction to Perceptron
  • Neural Network Activation Functions
    Cost Functions
  • Gradient Descent Back-propagation
  • Creation of Neural Network – Operation, Placeholder and Variables
  • TensorFlow Tutorial – Deep Learning Using TensorFlow
  • Introduction to TensorFlow
  • TensorFlow Basic Syntax
  • TensorFlow Graphs
  • TensorFlow Playground
    Variables and Placeholders
  • TensorFlow – A Neural Network
  • TensorFlow Classification Example
  • TF Classification Exercise
  • Saving and Exporting Models in productions to mobile App
  • MNIST Basic Approach
  • CNN Theory
  • RNN Theory
  • Vanishing Gradients, LSTM Theory
  • RNN with TensorFlow
  • GAN Theory
  • Generator Network
  • Discriminator Network
  • GAN with CNN cascading
  • Deep Reinforcement Learning Theory
  • Reward Systems
  • Discount and accumulation
  • Object Detection Tutorial in TensorFlow: Real-Time Object
    Detection

Duration:

3 Months (Weekends )

Register now for Faculty Development Program at PCCOE!

Deep Machine Learning

  • Python-Julia Programming

  • Data visualization

  • Machine Learning

  • Deep Learning

  • CNN-convolutional neural network

  • GAN-generative adversarial network

  • RNN-recurrent neural network

  • ADASadvanced driving assistance system

Modules
+
Exercises
+
Articles
Hrs/Week
Training
40 Hrs

Duration

Deep ML

Certification

Course Objective :

Machine learning is all about combining human intelligence with enormous computational power of computer to solve the problems that matters the most to the society. This course will teach you the end-to-end process of data analysis and DEEP machine learning – neural network on it to create model for prediction. We will also teach you how to extract and identify useful features that best represent your image, sound samples, and data to train DEEP learning model to deploying that model to applications on web and mobile apps, additionally we teach you expert secrets to achieve the performance of 99% accuracy in a limited time. We will also teach you how to extract and identify useful features that best represent.

What Will I Learn?

  • Math for Machine Learning
  • Application development for ML
  • Image and Video Processing
  • Speech Processing
  • NLP-NLU-NLG
  • Data Visualization

Includes:

  • 70 Hrs of Classroom
  • 15+ coding Exercises
  • 7+ Projects
  • 5+ Articles
  • 6 Hrs/Week

Course Structure

  • Statistics – Mean, Median, Mode, standard Deviation and variances,
    co-corelation coefficient, data distribution and plotted inferences
  •  Probability- Sets, Addition and multiplication of probability, exclusive,
    exhaustive, mutually exclusive, Bayes theorem and application,
    probability distribution function, probability and log loss function
  •  Linear and polynomial algebra and Plotting and Graphs Matrix and
    Matrices Discreet Structure
  •  Co-ordinate Geometry- line, curve, circle, parabola etc. 5. Function
    Limits and Continuity
  • APPLIED Calculus- APPLIED Differentiation and Integration,
    differential equation
  • Applied Logarithms
  • for imaging processing and Convolutional neural network
  • Signals and system – signal representation (discreet and continuous
    time function)
  • Digital signal processing – conversion of analogy to digital signal and
    performing different filters over digitise signal to extract information such
    as speech processing
  • Digital Image/audio/video processing – Image encoding-decoding
    and applying different types of filter over images to extract the desired
    results
  • Fuzzy logics basic- Algorithm used for Resolving error and paradox
    when machine learning almost fails.
  •  Pre-Processing on Data set.
  • Learning setup introduction.
  • Practical learning.
  • Supervised learning setup (Practical) Linear Regression and
    Gradient descent
    Practical: Price prediction of Pizza
  • Logistic Regression Generative learning algorithms
    Practical: Image to Text converter for modern billing system
  • Gaussian discriminant analysis
  • Naive Bayes.
  • Decision Tree algorithms
  • Support Vector Machines
  • Support Vector Machine with Kernel Trick
    Practical: Face detection
  • Model selection and feature selection. Evaluating and debugging
    learning algorithms.
  • Clustering. K-means. Dimensionality Reduction Anomaly Detection
    Projects :
    a. Cancer Prediction with limited amount of dataset
    b. Star prediction from NASA Dataset
    c. Financial market analysis
    d. Sentimental analysis
    e. Vehicles counting using open CV
    f. Real-time Audio detection
    g. Image search Crawler with NLP
    h. Anomaly Detection in the field of Cyber Security
    i. Data clustering in BIG DATA
  • Introduction to Perceptron
  • Neural Network Activation Functions
    Cost Functions
  • Gradient Descent Back-propagation
  • Creation of Neural Network – Operation, Placeholder and Variables
  • TensorFlow Tutorial – Deep Learning Using TensorFlow
  • Introduction to TensorFlow
  • TensorFlow Basic Syntax
  • TensorFlow Graphs
  • TensorFlow Playground
    Variables and Placeholders
  • TensorFlow – A Neural Network
  • TensorFlow Classification Example
  • TF Classification Exercise
  • Saving and Exporting Models in productions to mobile App
  • MNIST Basic Approach
  • CNN Theory
  • RNN Theory
  • Vanishing Gradients, LSTM Theory
  • RNN with TensorFlow
  • GAN Theory
  • Generator Network
  • Discriminator Network
  • GAN with CNN cascading
  • Deep Reinforcement Learning Theory
  • Reward Systems
  • Discount and accumulation
  • Object Detection Tutorial in TensorFlow: Real-Time Object
    Detection

Duration:

3 Months (Weekends )

Facebook
Twitter
LinkedIn
Instagram
Hire Talent