Machine Learning and Deep Learning in AI – Explained

Deal Score+1
Deal Score+1

Machine Learning and Deep Learning – Firstly, It’s almost harder to understand all the acronyms that surround artificial intelligence (AI) than the underlying technology. Secondly, couple that with the different disciplines of AI as well as application domains and it’s easy for the average person to tune out and move on. Thirdly, Below we attempt to explain the important parts of artificial intelligence and how they fit together. Fourthly, at Sonix we are specifically focused on automatic speech recognition so we explain the key technologies with that in mind.

First, let’s start with some of the most commonly used acronyms and their definitions:

  • Artificial Intelligence (AI)the broad discipline of creating intelligent machines
  • Machine Learning (ML) refers to systems that can learn from experience
  • Deep Learning (DL) –refers to systems that learn from experience on large data sets
  • Artificial Neural Networks (ANN)refers to models of human neural networks that are designed to help computers learn
  • Natural Language Processing (NLP) -refers to systems that can understand language
  • Automated Speech Recognition (ASR)refers to the use of computer hardware and software-based techniques to identify and process human voice.
≡ Deep Learning vs Machine Learning • What's the difference?

Approach in AI – Machine Learning and Deep Learning

  • Artificial intelligence (AI) is the overarching discipline that covers anything related to making machines smart. Firstly, whether it’s a robot, a refrigerator, a car, or a software application, if you are making them smart, then it’s AI. Secondly, Machine Learning (ML) is commonly used alongside AI but they are not the same thing. Thirdly, ML is a subset of AI and ML refers to systems that can learn by themselves. Fourthly, systems that get smarter and smarter over time without human intervention. Deep Learning (DL) is ML but applied to large data sets. Most AI work now involves ML because intelligent behavior requires considerable knowledge, and learning is the easiest way to get that knowledge. The image below captures the relationship between AI, ML, and DL.

Techniques of ML Approach

Difference Between Machine Learning and Deep Learning - GeeksforGeeks

There are many techniques and approaches to ML. One of those approaches is artificial neural networks (ANN), sometimes just called neural networks. A good example of this is Amazon’s recommendation engine. Amazon uses artificial neural networks to generate recommendations for its customers. It suggests products by showing you “customers who viewed this item also viewed” and “customers who bought this item also bought”. Amazon assimilates data from all its users browsing experiences and uses that information to make effective product recommendations.

At Sonix we convert audio to text using machines. The principle underlying technologies are automated speech recognition (ASR) and natural language processing (NLP). ASR is the processing of speech to text whereas NLP is the processing of the text to understand the meaning. Because humans speak with colloquialisms and abbreviations it takes extensive computer analysis of natural language to drive accurate outputs.

ASR and NLP fall under AI. ML and NLP have some overlap as ML is often used for NLP tasks. ASR also overlaps with ML. It has historically been a driving force behind many machine learning techniques.

Machine Learning vs. Deep Learning: What's the Difference? - IEEE  Innovation at Work

ML, DL and AI Projects Successful in The Industry

    • Hear from other Sonix users about how they record high-quality audio
    • Five reasons you should be transcribing your audio and video files
    • How did we get to where we are today in speech recognition? Sonix explains
    • The metallic, tin-like sound you hear in your audio is an unwelcome annoyance
    • Background noise is annoying and lowers the accuracy of your transcript
    • Background noise is distracting in videos and doesn’t transcribe well
    • Room tone is the naturally occurring noise in the environment during your recording
    • Sonix is the best online audio transcription service for 2021
    • Sonix is the best online video transcription service. It’s fast, accurate, and affordable.
Does Deep Learning Really Require “Big Data”? — No! | by Zach Monge, PhD |  Towards Data Science

Artificial Intelligence (AI) Human Intelligence Exhibited by Machines

  • Firstly, intelligence exhibited by machines
  • Secondly, broadly defined to include any simulation of human intelligence
  • Thirdly, expanding and branching areas of research, development, and investment
  • Includes robotics, rule-based reasoning, natural language processing (NLP), knowledge representation techniques (knowledge graphs)

Machine Learning (ML) An Approach to Achieve Artificial Intelligence

  • Subfield of AI that aims to teach computers the ability to do tasks with data, without explicit programming
  • Uses numerical and statistical approaches, including artificial neural networks to encode learning in models
  • Models built using “training” computation runs or through usage

Deep Learning (DL) A Technique for Implementing Machine Learning

  • Subfield of ML that uses specialized techniques involving multi-layer (2+) artificial neural networks
  • Layering allows cascaded learning and abstraction levels (e.g. line -> shape -> object -> scene)
  • Computationally intensive enabled by clouds, GPUs, and specialized HW such as FPGAs, TPUs, etc.

Data Science — Scientific methods, algorithms and systems to extract knowledge or insights from big data

  • Also known as Predictive or Advanced Analytics
  • Algorithmic and computational techniques and tools for handing large data sets
  • Increasingly focused on preparing and modeling data for ML & DL tasks
  • Encompasses statistical methods, data manipulation and streaming technologies (e.g. Spark, Hadoop)
  • Key skill and tools behind building modern AI technologies

One graphic to explain AI, ML, DL and Data Science

Your smartphone, your house, your car, and your bank all use artificial intelligence on a daily basis. Sometimes it’s easy to understand when you ask Siri, Cortana or OK Google to get you directions. Sometimes it’s less obvious, like when you make an abnormal purchase on your credit card and don’t get a fraud alert from your bank. AI, ML and DL are everywhere and Data Science is the interdisciplinary field of methods to extract the knowledge needed. All these technologies are making a huge difference in our lives every day and evolving fast by a magnitude of people working to improve them consistently.

We will be happy to hear your thoughts

Leave a reply

Compare items
  • Cameras (0)
  • Phones (0)
  • Laptops (0)