Featured Post

8 Ways to Optimize AWS Glue Jobs in a Nutshell

Image
  Improving the performance of AWS Glue jobs involves several strategies that target different aspects of the ETL (Extract, Transform, Load) process. Here are some key practices. 1. Optimize Job Scripts Partitioning : Ensure your data is properly partitioned. Partitioning divides your data into manageable chunks, allowing parallel processing and reducing the amount of data scanned. Filtering : Apply pushdown predicates to filter data early in the ETL process, reducing the amount of data processed downstream. Compression : Use compressed file formats (e.g., Parquet, ORC) for your data sources and sinks. These formats not only reduce storage costs but also improve I/O performance. Optimize Transformations : Minimize the number of transformations and actions in your script. Combine transformations where possible and use DataFrame APIs which are optimized for performance. 2. Use Appropriate Data Formats Parquet and ORC : These columnar formats are efficient for storage and querying, signif

The Growth of Machine Learning till TensorFlow

The Internet and the vast amount of data are inspirations for CEOs of big corporations to start to use Machine learning. It is to provide a better experience to users.

How TensorFlow Starts

Let us take Amazon, online retail that uses Machine learning. The algorithm's purpose is to generate revenue. Based on user search data, the ML application provides information or insights.

The other example is the advertising platform where Google is a leader in this line. Where it shows ads based on the user movements while surfing the web. These are just a few, but there are many in reality.

TensorFlow is a new generation framework for Machine Learning developers. Here is the flow of how it started.
Machine Learning


Evolution

Evolution of TensorFlow

Top ML Frameworks

Torch

  • The torch is the first framework developed in 2002 by Ronan Collobert. Initially, IBM and Facebook have shown much interest.
  • The interface language is Lua.
  • The primary focus is matrix calculations. It is suitable for developing neural networks.

Theano

  • It is developed in 2010 by the University of Montreal. It is highly reliable to process graphs (GPU).
  • Theano stores operations in a data structure called a graph, which it compiles into high-performance code. It uses Python routines.

Caffe

  • This framework is much popular in processing Image recognition.
  • Caffe is written in C++.
  • It is popular in Machine Learning and Neural networks.

Keras

  • It is well known for developing neural networks. 
  • The real advantages or simplicity and easy development.
  • Fran├žois Chollet created Keras as an interface to other machine learning frameworks, and many developers access Theano through Keras to combine Keras's simplicity with Theano's performance.

TensorFlow

This is developed by Google in 2015. You can use TensorFlow on Google cloud. It supports Python heavily. The core functions of this framework developed in .C++

Takeaways.

  1. The story of Machine Learning started in the 18th century.
  2. Python is the top interface language in the major ML frameworks.
  3. Python is the prime language you need for 20th-century Data science projects.

Comments

Popular posts from this blog

How to Fix datetime Import Error in Python Quickly

How to Check Kafka Available Brokers

SQL Query: 3 Methods for Calculating Cumulative SUM