Training Archives - State Technologies

Applications of AI for Anomaly Detection

2 hrs

Learn to detect anomalies in large data sets to identify network intrusions using supervised and unsupervised machine learning techniques, such as accelerated XGBoost, autoencoders, and generative adversarial networks (GANs).
PREREQUISITES: Experience with CNNs and Python
TOOLS AND FRAMEWORKS: Keras, GANs
LANGUAGES: English
DURATION: 2 hours

Clustering

2 hrs

Learn the theoretical foundations of clustering along with fundamental and advanced clustering methods such as distance based, iterative, hierarchical, continuous and categorical, density based methods. Dive into a deeper analysis with measures to analyze quality of clustering and its applications.
PREREQUISITES: Basic machine learning and python.
TOOLS AND FRAMEWORKS: Python, sci-kit learn, Tensor flow.
LANGUAGES: English
DURATION: 2 hours

Coarse-to-Fine Contextual Memory for Medical Imaging

2 hrs

Learn how to improve traditional architectures using coarse-to-fine context memory. Apply it to medical image segmentation and classification tasks.

PREREQUISITES: Experience with CNNs and long short-term memory (LSTM)
TOOLS AND FRAMEWORKS:TensorFlow
LANGUAGES:English
DURATION:2 hours

Deep Learning

4 hrs

PREREQUISITES:Neural Networks and python
TOOLS AND FRAMEWORKS:Tensorflow, Keras, PyTorch
LANGUAGES:English
DURATION:4 hours

Deep Learning For Creating Digital Content

2 hrs

Learn character animation, transferring styles between images and videos, denoising images using neural networks.

PREREQUISITES: Basic familiarity with deep learning concepts, such as CNNs and experience
with Python.
TOOLS AND FRAMEWORKS: TensorFlow, Torch .
LANGUAGES: English
DURATION: 2 hours

Deep Learning for Intelligent Video Analytics

2 hrs

Learn to develop deep neural networks for object detection, localization and tracking.

PREREQUISITES: Experience with deep networks (specifically variations of CNNs) and intermediate level experience with C++ and Python.
TOOLS AND FRAMEWORKS: TensorFlow
LANGUAGES: English
DURATION: 2 hours

Deep Learning Network Optimization

4 hrs

PREREQUISITES: Neural Networks and python.
TOOLS AND FRAMEWORKS: Tensorflow, Keras, PyTorch
LANGUAGES: English
DURATION: 4 hours

Introduction Of Machine Learnig (Advance)

2 Days | 18 hrs

Mathematics for Machine Learning
1. Introduction to Calculus, Linear Algebra, Probability, Statistics and Random Variables
2. Introduction to Python, numpy, pandas etc.
3. Python assignments.

Machine Learning Basics
1. Fundamentals of Machine Learning
2. Application in Machine Learning- Classification, Regression etc.
3. Introduction to the theory and algorithms of :
→ Supervised Learning
→ Semi Supervised Learning
→ Unsupervised Learning
→ Graphical Models
→ Predictive Modelling

Practical Machine Learning-Frameworks
1. Machine Learning Frameworks :
→ Google COLAB
→ Sci-kit-learn
→ TensorFlow
→ PyTorch
→ Keras
2. Industry grade tools and technologies for implementing a practical machine learning project
3. Assignments – classification, regression and mathematical models
Quiz

Neural Network and Deep Learning
1. Introdution to theory of neural networks and stochastic gradient descent
2. Deep neural networks, CNN, RNN, Auto Encoders
3. LSTM, GAN, Capsule networks

Practical Machine Learning – Your own models
1. Implementing a Neural Network from scratch
2. Implementing a Deep Neural Network (CNN, RNN, GAN) in Tensorflow/PyTorch
3. Developing AI projects and practical caveats in implementing machine learning models
4. Organizing Machine Learning Projects

Research and Applications
1. Applications of AI in Industry and Academia
2. Computer Vision
3. Natural Language Processing
4. What’s hot in AI research – a discussion on state of the art and recent trends in AI
Quiz

Introduction Of Machine Learnig (Basic)

Day 1 | 8 hrs

Mathematics for Machine Learning
1. Introduction to Calculus
2. Introduction to Linear Algebra
3. Introduction to Probability & Statistics

Machine Learning Basics
1. Fundamentals of Machine Learning
2. Machine Learning Practical Applications: Classification, Regression etc.
3. Supervised Learning
4. Semi Supervised Learning
5.Unsupervised Learning
6. Neural Networks and Deep Learning

Practical Machine Learning
1. Machine Learning Frameworks : Python, Google COLAB, TensorFlow, Pytorch, Keras
2. Code Classification and Time series Prediction Models
3. Implementing a Neural Network from Scratch

Quiz