Be Grateful

Kinetic Data Science
Kinetic Data Science
  • Home
  • ePortfolio
  • Computer Vision
  • Quantum
    • Quantum Software
    • Quantum Hardware
  • Data Visualization
    • US Population Report
    • Cancer Data
    • US Tornado Data
  • BI Projects
    • Employee Attrition
  • Public Datasets
  • Data Science
    • Business Intelligence
    • Data Engineering
    • Data Warehousing
    • Data Visualization
    • Machine Learning and AI
  • Demo
  • Bacquets
  • More
    • Home
    • ePortfolio
    • Computer Vision
    • Quantum
      • Quantum Software
      • Quantum Hardware
    • Data Visualization
      • US Population Report
      • Cancer Data
      • US Tornado Data
    • BI Projects
      • Employee Attrition
    • Public Datasets
    • Data Science
      • Business Intelligence
      • Data Engineering
      • Data Warehousing
      • Data Visualization
      • Machine Learning and AI
    • Demo
    • Bacquets
  • Sign In

  • My Account
  • Signed in as:

  • filler@godaddy.com


  • My Account
  • Sign out

Signed in as:

filler@godaddy.com

  • Home
  • ePortfolio
  • Computer Vision
  • Quantum
    • Quantum Software
    • Quantum Hardware
  • Data Visualization
    • US Population Report
    • Cancer Data
    • US Tornado Data
  • BI Projects
    • Employee Attrition
  • Public Datasets
  • Data Science
    • Business Intelligence
    • Data Engineering
    • Data Warehousing
    • Data Visualization
    • Machine Learning and AI
  • Demo
  • Bacquets

Account


  • My Account
  • Sign out


  • Sign In
  • My Account

Making Data Meaningful with Business Intelligence

Making Data Meaningful with Business Intelligence Making Data Meaningful with Business Intelligence

Data Engineering

ELT

Python & Anaconda

SQL and Database

ETL Tools. Extract Transform Load (ETL) is a category of technologies that move data between systems. 

SQL and Database

Python & Anaconda

SQL and Database

 Structured Query Language (SQL) is the standard language for querying relational databases.

Python & Anaconda

Python & Anaconda

Python & Anaconda

  Python. Python is a general purpose programming language used in Data Science.  Anaconda  open-source ecosystem, the platform of choice for Python data science. 

Spark and Hadoop

Spark and Hadoop

Python & Anaconda

 Spark and Hadoop work with large datasets on clusters of computers.  

Data Lake

Spark and Hadoop

Data Security

Data Lake is a centralized repository that allows you to store all your structured and unstructured data at any scale. 

Data Security

Spark and Hadoop

Data Security

Data Security Knowledge of data protection to proactively prevent stolen data and ransomware.

Data Science

Data Mining

Dynamic Visualization

Data Mining

 Data mining Public Data Sets is an interdisciplinary subfield of computer science and statistics with an overall goal to extract information (with intelligent methods) from a data set and transform the information into a comprehensible structure for further use. 

Big Data

Dynamic Visualization

Data Mining

Big data is a field that treats ways to analyze, systematically extract information from, or otherwise deal with data sets that are too large or complex to be dealt with by traditional data-processing application software 

Dynamic Visualization

Dynamic Visualization

Dynamic Visualization

Dynamic Visual is a representation of the data and use of interactive web based charts and graphs. It gives the user insight to make knowledge-based decisions.

Data Warehouse

Quantum Data Science

Dynamic Visualization


Data Warehouse (DW) a system used for reporting and data analysis and is considered a core component of business intelligence. DWs are central repositories of integrated data from one or more disparate sources. 

ML and IA

Quantum Data Science

Quantum Data Science

 Machine learning (ML) is the study of computer algorithms that can improve automatically through experience and by the use of data.  It is seen as a part of AI

Quantum Data Science

Quantum Data Science

Quantum Data Science

Quantum Data Scientists may also be motivated to learn more quantum computing in order to study quantum machine learning. 

Data Mining & Power BI

US Population map

Population Report

US Data Population Visualization

US Population Data

Compare State by State

Compare State by State

Map the year over year population growth by state with interactive maps

Compare State by State

Compare State by State

Compare State by State

Select any number of states to compare data side by side with other states 

Data Tables

Compare State by State

Data Tables

See the data organized in table format to easily compare and view data 

US Cancer Data

Cancer Visualization Data By State

Cancer Data

Year Over Year Growth Charts

Year Over Year Growth Charts

Building Cancer Data Models To Help Join the Fight Against Cancer

Year Over Year Growth Charts

Year Over Year Growth Charts

Year Over Year Growth Charts

See How Cancer is Effecting the Unites States by Trending growth Sate by State

Cancer Heat Map by Type

Year Over Year Growth Charts

Cancer Heat Map by Type

Unites States Heat Map of  Cancer by Types Calculated Per-Capita   

Data Science and Beyond

The future of technology will greatly be shaped by A.I., Deep Learning, Neural Networks, and Quantum Computing.  Below are a few examples that demonstrate these technologies.

Computer Vision and Object Detection

Computer Vision A.I.

Object Detection with a Phone

Using a Standard iPhone, we can send the video feed through a Neural Network that can identify over 80 different classes of object detection with Computer Vision.  

Object Detection with a Drone

Using a DJI Tello Drone we can program a lightweight Neural Network for Object Detection into the drone itself.  The Drone can identify over 80 objects with this NN and computer vision.

Drone Object Tracking

Now that we have trained the drone in Object Detection, we can then program the Drone to follow objects, people, even facial recognition.

How is Computer Vision Built?

We use Convolutional Neural Networks built with many layers known as Deep Learning to train computers how to identify objects.  Above you see an example of a NN we have trained that has over 80 classes like, People, Cars, Plants, Bicycles, etc.  


To train models with Deep Learning we need a decent amount of horsepower to fully train the model in Object Detection A.I.

Deep Learning

Deep learning attempts to mimic the human brain—albeit far from matching its ability—enabling systems to cluster data and make predictions with incredible accuracy. What is deep learning? Deep learning is a subset of machine learning, which is essentially a neural network with three or more layers. These neural networks attempt to simulate the behavior of the human brain—albeit far from matching its ability—allowing it to “learn” from large amounts of data. While a neural network with a single layer can still make approximate predictions, additional hidden layers can help to optimize and refine for accuracy.  Deep learning drives many artificial intelligence (AI) applications and services that improve automation, performing analytical and physical tasks without human intervention. Deep learning technology lies behind everyday products and services (such as digital assistants, voice-enabled TV remotes, and credit card fraud detection) as well as emerging technologies (such as self-driving cars).

Find out more from IBM

TensorFlow Deep Learning Technology

The Software

Deep Learning Technology

The Software

TensorFlow is an end-to-end open-source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.

The hardware

Deep Learning Technology

The Software

Nvidia is the leader ACCELERATED MACHINE LEARNING Hardware. GPU Deep Learning Increases model accuracy and directly impact the bottom line with highly optimized machine learning pipelines.

Deep Learning Technology

Deep Learning Technology

Deep Learning Technology

Heavily used by data scientists, software developers, and educators, TensorFlow is an open-source platform for machine learning using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them. This flexible architecture allows m

Heavily used by data scientists, software developers, and educators, TensorFlow is an open-source platform for machine learning using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them. This flexible architecture allows machine learning algorithms to be described as a graph of connected operations. They can be trained and executed on GPUs, CPUs, and TPUs across various platforms without rewriting code, ranging from portable devices to desktops to high-end servers.

CPU vs. GPU

Intel CPU

CPU's (central processing units) are genral purpose processors found in laptops, desktops, and servers.  They are known as all-purpose processing units.

Nvidia GPU

GPU's (Graphic Processing Unit) GPU's are indispensable for machine learning. Training models is a hardware intensive task, and a decent GPU will make sure the computation of neural networks goes smoothly. Compared to CPUs, GPUs are way better at handling machine learning tasks, thanks to their several thousand cores.

Intel CPU Deep Learning

The video below is an example of CPU deep learning.  This model has over 1 million parameters to learn with each EPOCH scan so it can detect skin cancer.  The System must study each set of over a million parameter 35 times! This is known as an Epoch step or Epoch scan.

Nvidia GPU Deep Learning

Above we saw each scan will take approximately 115 seconds each to complete.  That means on traditional Server/Cloud hardware each time we run the model it will take about a 1 hour and 10 minutes to complete.


Now let's run the model using TensorFlow and an Nvidia GPU.

With Intel i9 processor we can see that the model would take approximately 70 minutes to complete.

With Nvidia GPU the model takes 4 minutes to complete.

This is extremely valuable with Deep Learning because every time we make a change to the model, we must rerun it for accuracy.  This is especially useful when building a model because you will run the model a considerable number of times tuning the hyperparameters for accuracy.

Copyright © 2021 Kinetic Data Science - All Rights Reserved.

  • Home
  • ePortfolio
  • Computer Vision
  • Quantum Software
  • Quantum Hardware
  • US Population Report
  • Cancer Data
  • US Tornado Data
  • Employee Attrition
  • Public Datasets
  • Data Visualization

Powered by ✟ Data Science

This website uses cookies.

We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.

DeclineAccept