The music is too dramatic for the topic 😂

since when did we call "input layers" as "input neurons"? I think you're the only one who thought of that

I would say that we meed to think of a neural network as a function. The inputs are just variables from the observations row, and the number of these "orange dots" or inputs are just the features of X observation (columns are features and rows are observations). Difference between this and a linear regression function is the fact that a neural network is a function that can twist and turn to learn any pattern of data (a universal function approximator)

here in final diagram, input is changed as rectangle to represent it as a placeholder but output is still shown as green circle how are output's represented?

wrong definition of noise and border point.

Great explanation but the video blurs in between and everything becomes unreadable. Please rectify that if possible.

reported for misinformation...

Best best biggest. I need it

Bro creates a problem 😊

I subscribed

Underrated channel. Superb teaching. No channel comes even close to how eloquently he is educating. Can we expect complete courses on machine learning, deep learning and new age ai trends like agi, llm, etc? Can You bring a complete course on developing end-end ai based projects? Forgive me as I asked for so many things, it's because I have never experienced an educator like You Sir.

Why do you think any one thinks that the input layer represented as circle is called a neuron? I have watched many videos and didn’t find any such thing. The diagram is repeated like this to make it look appealing. Don’t create unnecessary misconceptions to get views and likes!

What the fuck man? Everybody knows this even my 8 years old niece

Hi Faruk, very good explanation. need to connect with you about my carrier and road map and it will take 10 to 20 min , If this fine I can connect ?

That’s a really good point about the activation or transform function

No shit sherlock

"They are even called input neurons" then proceeds to write "Input Neurons" himself.

Very well explained. Thanks for creating such videos.

Meh, disagree. While it's universally the case that Hidden nodes have non-linear activation (otherwise what's the point), it is often the case that Output nodes have a completely different activation function or none at all, just like input nodes. Are you going to argue that they are not Neurons too? Sometimes? But my preferred way to view it is not to say "there is no activation function" but to say "the activation function is id(x)=x". There you go, now it's a Neuron. Everything is a neuron. And heck, sometimes Input neurons *do* have activation functions. It's often the case that the data needs to go through some sort of normalization/serialization process before it is ready to be placed in the network. That's fundamentally activation. As for adding rectangles to the graph: Go for it, draw it however you like to help. I thought different colors and the fact that they are at the extreme ends of the graph were enough to illustrate that they were special, but you do you.

Who said input layer as neuron layer? 😅

Lame indian genius

circle is for something had computation inside, circle represent a function, process, and??? rectangle has no computation inside this represent data input/output help to define it I already maxed all my token to learn with AI, my local AI too stupid... :(

Great explanation interview-focused. Thanks a lot!

ironic

fantastic explanation sir

That is a great explanation, clear and crisp definitely focused on interview

Very good clarification

great lecture to know everything about the decision Tree for answering interview qs.

it is indeed an input layer it performs identity function with weights all 1.0 y = matmul(1.0*x, np.eye(...))) you will understand it is correctly when your MLP needs to be stacked on top of CNN layer for example.

Never ever EVER heard about that misconception

bro produced the problem and sold the solution

I think he created a problem and solved it

I had this problem today, I was confused about why CBOW had 2 layers but showed as 3. Chatgpt explained what you've said here. Your video had almost the perfect timing.

This is a bad video

Your way of teaching is quite good. It would be great help if you teach us ML algorithms practically on actual data.

Very good explanation. But I would say one thing is missing here. There is a subtle difference between a data scientist and a machine learning engineer. Data scientists mostly deal with the business data and ML engineers work in the process of building a product based on machine learning. It is true that there are lot of similarities between the task of a data scientist and a machine learning engineer. A data scientist can also create products and ML engineers can also work in the business domain. But still these are just possibilities. These are not specifications. Beginners often feel so much confused between these two things. And many of them started to think that two are similar. In current job market, the requirements of a data scientist and ML engineer are quite different. ML engineers need lot of software engineering skills along with machine learning skills. ML engineers are just a special kind of software engineers.

You deserve more views, thankyou bro.

🫡Hats off Sir.. You're the most valuable I've ever seen in my life.. The concepts explanation from scratch is god damn... It's precise & not deviating the content.. I'm very much impressed on your sharable knowledge in Machine learning ❤️❤️ Keep up the great work Sir.. Love from India 🫶

grate work

Nice work

I don't think it's a problem... People will be able to understand that with even the most basic knowledge of neural networks... People and if they are like me won't be focusing on the terms and terminologies(cuz I always find a hard time with them😢)...

Can we have a series of DS or ML roadmap? I'm confuse bcz they overlap. Wait r u @indiainpixels ?

That is true, hopefully you reach many informed people

great video

Just clicked on your video thinking another clikbait video . But I have to admit you proved me wrong. Hoping for more valuable content like this from you in future.

But if needed, you could generalize the transfer function to the input layer by considering it as a pass-thru transfer function. Thus the input layer could be considered as a neuron layer with a specific transfer function and you are safe from any "artificial" confusion.

funny

Thank you

🤓

This is correct, except that using "full neurons" for the input layer will still work just fine. You just fix the transfer and activation functions.