Hey guys welcome to the session by
Intellipaat. Now you guys must have come across the terms artificial intelligence, machine learning and deep learning and numerous
questions would have popped into your head, what exactly are they how they are
different from each other and what purpose do they serve. So today’s session
would help you to understand the difference between these three terms so
I’ll start off by asking you a very simple question, so tell me what is it
that makes humans intelligent, well we as humans can think learn and make
decisions and that is what what makes us intelligent. Now imagine if machines can
show human-like intelligence, a machine which can think and make decisions like
humans, that is truly amazing isn’t it? So artificial intelligence is basically
that field of computer science which emphasizes on the creation of
intelligent machines which can work and react like humans. So now that we know
what artificial intelligence is, let’s see where do machine learning and deep
learning fit in. So you can consider artificial intelligence to be the
broader umbrella and machine learning and deep learning to be a subset of it
or you can also say that machine learning and deep learning are a means
to achieve artificial intelligence. Now let’s see what machine learning is. So
machine learning is basically the subset of artificial intelligence where we
teach a machine how to make decisions with the help of input data so we’ll
understand machine learning with this little example. So what do you see over here, what is this exactly? well it’s a bird and what about this, this again is a bird
and this? well this too is a bird. Now how do you all of these are birds? Well as a
kid you might have come across a picture of a bird and you would have been told
by your kindergarten teacher or your parents that this is a bird and your
brain learned that anything which looks like that is a bird and that is how our
brain functions. But what about a machine now if I take in this image of the bird
and feed it to a machine will it be able to identify it as a bird? So this is
where machine learning comes in so what I’ll do is I’ll take all of these images
of the birds and keep on feeding them to the machine until it learns
all the features associated with it and once it learns all the features
associated with it I’ll give it new data to determine how
well it has learnt or in other words first I’ll feed in training data to the
machine so that it can extract or learn all the features associated with the
training data and once the learning is done I’ll give it new data or the test
data to determine how well the learning is done and this is the underlying
concept of machine learning. Now let’s head on to deep learning, so deep
learning is the subset of machine learning where we develop intelligent
algorithms which mimic human brain. So now the question which arises over here
is how do we mimic human brain? Well to answer that let me ask another question.
So what is the brain composed of? Well a brain is primarily composed of neurons
Isn’t it and these neurons send and receive electrochemical signals so we
have a neuron over here and the electrochemical signals are received
through the dendrite, the processing of these signals is done in the cell body
and the output of these input signals is sent to other neurons to the axon and if
our task is to mimic human brain all we have to do is create artificial neurons
and these artificial neurons work the same way as biological neurons. So to
implement deep learning we’ll have to create artificial neural
networks and these artificial neural networks comprise of an input layer, a
hidden layer and an output layer so all of the inputs are received through the
input layer and the processing is done in the hidden layer and the final output
is received through the output layer and to sum it up artificial intelligence is
the broader umbrella, machine learning is the sub set of artificial intelligence
and deep learning is the sub set of machine learning and machine learning
and deep learning are basically methods to achieve artificial intelligence. So
guys this brings us to the end of the session and do stay tuned to Intellipaat youtube channel for more such informative videos.

11 thoughts on “AI vs Machine Learning vs Deep Learning | AI vs ML vs DL | Intellipaat”

  1. Got a question on Artificial Intelligence, Machine Learning or Deep Learning? Do write it in the comment and you will get a response immediately by our expert. For Artificial Intelligence, Machine Learning and Deep Learning training & certification, call us at US: 1800-216-8930 (Toll Free) or India: +917022374614. You can also write us at [email protected]

  2. Hope you learned something new from this AI vs ML vs DL video. Please be kind enough to like the video and subscribe the channel. Also feel free to ask your doubt in the comment section below.

  3. ML is learning data presented to machine, i.e. learning set of bird images to classify a bird, and recognising unseen bird image to correctly classify it as bird. There are two types of learning, supervised and unsupervised. Former method requires data that is already classified by humans, where as later compares data with itself for classification of data.
    DL is creating deeper abstract concept from data. E.g. concept of flying in general, which could be developed in machines from both birds and aeroplanes. Birds and aeroplanes together makes this concept in machines at deeper level and hence the word DL. We may not explicitly present concept of flying to machines, but DL techniques should generate them internally automatically. I.e. Learning deeper abstract concepts from data.
    Neural networks can be used for both ML ance DL, it is one of the tools.
    AI focuses more on decision making rather than learning. It uses concepts it has learned to do so.

  4. Thank you for the upload.
    I wonder what might be the DL training-steps (or algorithm) for the ML techniques used by the AI described in the video.

  5. The major problem i face it what code do I have to write to complete a project.
    For example I want to make some project, How will I decide that for this purpose I need to write only ML code or AI code or everything combined.

Leave a Reply

Your email address will not be published. Required fields are marked *