Artificial Neural Networks(ANN) Made Easy
What you'll learn
- ANN Introduction
- ANN Model Building
- ANN Hyper parameters
- Fine-tuning and Selecting ANN models
- Shallow and Deep Neural Networks
- Building ANN Models in Python, TensorFlow and Keras
- Basic High School Mathematics
- Basic Statistics like Mean, Median and Variance
Course Covers below topics in detail
Quick recap of model building and validation
Introduction to ANN
Hidden Layers in ANN
Back Propagation in ANN
ANN model building on Python
Building ANN models in TensorFlow
Regularization in ANN
Learning Rate and Momentum
Basics of Deep Learning
Pre-requite for the course.
You need to know basics of python coding
You should have working experience on python packages like Pandas, Sk-learn
You need to have basic knowledge on Regression and Logistic Regression
You must know model validation metrics like accuracy, confusion matrix
You must know concepts like over-fitting and under-fitting
In simple terms, Our Machine Learning Made Easy course on Python is the pre-requite.
Datasets, Code and PPT are available in the resources section within the first lecture video of each session.
Code has been written and tested with latest and stable version of python and tensor-flow as of Sep2018
Who this course is for:
- Beginners in Machine Learning
- Beginners in TensorFlow
- Beginners in Deep Learning
- Data Science Aspirants
- Computer Vision students
- Engineering , Mathematics and science students
- Data Analysts and Predictive Modelers
Statinfer is the data science e-learning solutions provider. We provide online and class room training on leading data science tools and techniques.
Our focus is on data analytics, machine learning, and AI. The tools that we work on are R, Python, Tensor Flow and Spark.
Statinfer is created by data scientists who understand the dynamics of the current business.
Our courses are not merely academic, instead, there are many industrial applications and examples. The creators assembled the course, well studied the topics with a clear understanding and had designed the curriculum.
Each course has ample amount of self-practicing labs, quizzes and projects on real data to get an exposure to real world problems.