IT TRAINING

Artificial Neural Networks, Machine Learning, Deep Thinking

If you ever wanted to know what Machine Learning, Data Science is about, this course is for you.

Artificial Intelligence is transforming multiple industries, take advantage.

Who needs to attend

Who needs to attend?

what you will learn

What you will learn

Some of the key skills and concepts you’ll get with this course:

  • You’ll be able to understand and write Python
  • Create pretty plots and impress your manager
  • Load, process and display data with Python Pandas (sources include csv, Excel files, HTML, etc.)
  • Understand key concepts of Machine Learning and Deep Learning
  • Predict who survives the Titanic
  • Build an image classifier for Hand written digits and Fashion Clothes
  • Through the course you’ll see how all these concepts are applied in industry and get practical advice.
Prerequisites

Prerequisites

  • Phyton
Course outline

Course Outline

Machine Learning Introduction – algoritmi clasici de ML si Deep Learning

  • Definitions
  • What is it used for
  • Machine Learning Pipeline
  • Types of Machine Learning
  • ** Supervised Learning
  • ** Unsupervised Learning
  • ** Reinforcement Learning
  • Summary of tools that we need to work with (Python, Numpy, etc)

Python and Jupyter Notebook

  • Introduction
  • Python Crash course
  • Python Packages
  • Virtual Environments
  •  Anaconda/miniconda/conda
  • Jupyter Notebook Introduction

Numpy Python Library

  • Introduction
  • Arrays
  • Indexing
  • Operations

Pandas Python Library for Data Analysis

  • Introduction
  • Panda Series
  • Panda Frames
  • Data Input

Matplotlib Python Library for Data Visualization

  • Introduction
  • Basic plotting
  • Saving plots
  • Loading, displaying images

Seaborn Python Library for Data Visualization

  • Introduction
  • Plots
  • ** Distribution Plots
  • ** Categorical Plots
  • ** Matrix Plots

Supervised Learning

  • What is a dataset
  • Splitting the dataset (train/val/test)
  • ** Notes on the ability to generalize (Generalization)
  • Feature selection
  • ** K Means Clustering
  • Bias Variance Tradeoff
  •  Overfitting
  •  Underfitting
  • What is an outlier?
  • How do we perform? Confusion Matrix

Supervised Learning algorithms

  • sci-kit learn introduction
  • Linear Regression, Polynomial Regression
  • Model Evaluation, Selecting the Best Model
  • Bias-Variance trade-off
  • Logistic Regression
  • Naive Bayes
  •  K Nearest Neighbors (KNN)
  • Decision Trees and Random Forests

Unsupervised Learning

  • Clustering
  •  K Means Clustering
  • Dimensionality Reduction
  • ** Principal Components Analysis (PCA)
  • ** Singular Value Decomposition (SVD)

Neural Networks

  • Definitions
  • ** Neuron
  • ** Multiple Neurons
  • ** Multiple Layers
  • ** Fully Connected Layers
  • ** Other Types of layers
  • Common Tasks (Image Classification, Object Detection, Segmentation, etc)
  • Number of parameters
  • Common Architectures

Introduction to Tensorflow and Keras API

  • Tensors
  • Computation Graph
  • Visualizing the Graph
  • Training

Image Classification with Tensorflow

  • Building a simple architecture by hand
  • MNIST Dataset
  • Data Augmentation

Follow on
There are no follow-ons for this course.

Certification programs
There are no certifications associated with this course.