What is Machine Learning? | Full Explained in Hindi

Monday, July 13, 2020

What is Machine Learning? | Full Explained in Hindi

Machine Learning का मतलब यह नहीं है कि Machine वास्तव में सोच रही है। Machine learning के पास statistics and pattern की पहचान के बारे में अधिक होता है एक सोच वाला robot होना जो दुनिया को संभालने वाला है। bots, big data, and artificial intelligence. में आपकी Insight.

इसलिए आपके द्वारा उपयोग किए जाने वाले Apps में machine learning अधिक से अधिक प्रचलित हो रही है। Voice recognition, driverless cars, या Recommendations से कुछ भी जो आपको Netflix, or Spotify पर मिलता है। Machine learning patterns in data पर चुनता है, और फिर यह उन पर Predictions based करता है पैटर्न।

Let me give you an example.

LEGO man, brick, LEGO man, brick, LEGO man...what do you think will come next?
Brick?

हाँ!
आपने सिर्फ एक Pattern को देखा है और उस Pattern के आधार पर एक Prediction की है। एक Machine Learning Algorithm वास्तव में इस के साथ भी अच्छा करेगा। सिवाय यह एक बहुत कुछ है कि हम भी एक Pattern है महसूस नहीं कर सकता के साथ बेहतर होगा। बहुत सारे और विभिन्न प्रकार के लेगो टुकड़ों के साथ बहुत सारे डेटा। यह एक सामान्य धागा मिल सकता है जहां हम नहीं कर सकते।

तो इसे Artificial Intelligence का एक हिस्सा क्यों माना जाता है? ठीक है, ऐसा इसलिए है क्योंकि Machine Learning हमारे द्वारा किए गए तरीके से बहुत कुछ सीखता है।

Think about children.
A parent reads a book to their child and points out a dog in the book.
this is us teaching a baby what a dog is.

Later mom and child are watching a cartoon, and mom points out a cartoon pup and says to the baby "hey, that's a dog".

Children and grandparents are walking down the street and they see a dog.
Grandparent says "that's a dog".

Our brains will see a new dog, and even though we've never that breed of dog before we'll still know that it's a dog.

Why?
Because we've seen enough patterns to make an assumption and a prediction.

Machine Learning के साथ, हम Machine को बहुत समान तरीके से सिखाते हैं।

Machine Learning मॉडल सिखाने के बजाय हम इसे Training कहते हैं। हम Machine Learning मॉडल को Training करते हैं। तो हम Machine सीखने के model को हजारों और कुत्तों के हजारों Photo देते हैं।

Machine Learning model कुत्तों की तस्वीरों में पैटर्न पर चुनता है। फिर जब हम इसे एक नई तस्वीर के साथ पेश करते हैं, तो यह समझता है कि वह भी एक कुत्ता है। जिसे हम Machine Learning model नहीं बताते हैं वह है "look out for two eyes, two ears, a nose, a tail, long hair, short hair".

That type of teaching for a machine is what we know as an algorithm.
Three things I want you to note about Machine Learning.

1. Machine Learning Still Needs Humans

Machine learning actually still requires a lot of human effort. We need human-labeled data for the machine to interpret. So we need to feed it images that humans have identified is in fact a dog. In the second part of machine learning, we need to see what its outputs are, and we need to validate if it's right or wrong. Just like if a baby points at a cat and says "hey this is a dog" we need a human there to say "no child". We need humans. And there's a whole industry around humans labeling data for machine learning.
Like this company, or this company, or this company.
Their whole purpose is to have humans annotate data and say "this is a stop sign, this is a truck" so that driverless cars can then learn to recognize things on the street.

2. Machine Learning Can Amplify Human Bias

The thing to note about machine learning is that machines can be quite biased. So remember I talked about humans feeding data to the machines? Well if humans input false or biased data, the machine is going to spit very biased data out. Amazon had this problem. Amazon taught a machine learning model to review all the resumes of people that apply to amazon jobs.
The problem being, is that humans were very biased in choosing some resumes over others. So the machine, what happened? It amplified the bias.

3. Machine Learning Isn't Leading to a Robot Takeover

The last thing I want you to remember about machine learning is that it's still a very nascent industry. A lot of companies are taking the lead in machine learning. Specifically, the ones that have lots of data - because you need data for machine learning.

So this includes, Google, Amazon....but machine learning right now isn't a sentient thinking machine. It's just looking at patterns and making predictions.

Thanks so much for reading this article.