What you think vs What is real.

Image for post
Image for post
Web

Suck behind the paywall? Click here to read the full story with my friend link!

So, 3 months ago, I woke up at 3 pm, earlier than usual, thinking about which movie to watch. Opened Facebook, saw some people posting about CodeCademy offering free Pro Memberships for Covid-19. Was kinda amazed and applied right away.

Web Developer Career Path

Now, after reading many reviews and articles, I decided that I’d study Web Development form the platform. Then, there were either courses that I’d have to enroll and complete or the whole Career Path. Not gonna lie, the career path seemed like a ton of work in the start but I eventually made up my mind to go for that rather than to manually choose what to study. Also, I feel like its easier when someone does the tough job for you i.e. The curriculum-making, etc. …


Deep Learning

A guide to tuning your Hyper Parameters to get the best accuracy.

Image for post
Image for post
Photo by Kumpan Electric on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

This article is actually a continuum of a series that focuses on the basic understanding of the building blocks of Deep Learning. Some of the previous articles are, in case you need to catch up:

Deep Learning is the branch of Artificial Intelligence where we let the model learn features on its own to get to a result. …


Deep Learning

Adapting your Learning Rate Parameter with time can make a huge difference! Let’s see how.

Image for post
Image for post
Photo by Simon Migaj on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

This article is actually a continuum of a series that focuses on the basic understanding of the building blocks of Deep Learning. Some of the previous articles are, in case you need to catch up:

Deep Learning in a field that is almost ruling the list of Most worked on industries, and the reason I see is the potential it has in the near future. I have mentioned this numerous times that we won’t have people driving taxis or people are the cash counter after 10 years, and all that work would be replaced by Machines. …


Deep Learning

This is used to speed up Gradient Descent.

Image for post
Image for post
Photo by Ramón Salinero on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

This article is actually a continual of previous series of articles. Here are links to the stories, if you will to come along.

Now, who doesn’t like Deep Learning? I suppose you do or why else would you be reading this article. But Deep Learning is just starting out these days, there ALOT that has to be discovered in the field.

Despite the rapid advancements and studies being done in the field, there’s is still a ton of stuff that we need to unveil.


Deep Learning

Use this to enhance your Deep Learning models!

Image for post
Image for post
Photo by Samuel-Elias Nadler on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

In the last post, we covered Exponentially Weighted Averages! Now, to further improve the model’s accuracy, we’ll discuss L2 regularization. Take a peek at my last post here:

‘Regularization is any modification we make to a learning algorithm that is intended to reduce its generalization error but not its training error.’ ~ Ian GoodFellow

Now, there are two types of Regularizations, L1 and L2. Sure, there are others too but these are the generally thought of when we talk about L regularizations. …


Deep Learning

Use this optimization to speed up your training!

Image for post
Image for post
Photo by Uriel SC on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

We all, ML Engineers or Data Scientists, love Data. Whenever we hear that we are getting more Data to use, it sounds like Heaven but

Not everything is as it seems.

“What is the drawback here?” ~ you might ask. So, we have our little CPU Processors, but some of the lucky ones among us have GPUs, but then too, the Computing Power is not skyrocketing and has a limit. The main drawback that I can think of is Too long Training time obviously.

Exponentially Weighted Averages

Let me explain this the way NG explained. Suppose you have the weather data of London. You want to able to predict weather on different days. The data might look something…


Use this optimization to speed up your training!

Image for post
Image for post
Photo by Mathew Schwartz on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

We all, ML Engineers or Data Scientists, love Data. Whenever we hear that we are getting more Data to use, it sounds like Heaven but

Not everything is as it seems.

“What is the drawback here?” ~ you might ask. So, we have our little CPU Processors, but some of the lucky ones among us have GPUs, but then too, the Computing Power is not skyrocketing and has a limit. The main drawback that I can think of is Too long Training time obviously.

Mini Batch Gradient Descent

Say you have a batch of 5,000,000 data inputs. Now, this would alone make a vector of 5,000,000 sizes, and should you think of efficiency when performing any Mathematical operation on a vector this big. What we do here? Ever heard of the saying “Baby steps”, this is essentially that. …


DEEP LEARNING

The best regularization technique out there.

Image for post
Image for post
Photo by Alina Grubnyak on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

We all know that Data is limited. Yeah, data is available in abundance today and is more than ever, but there still is a factor that it just isn’t unlimited data for anything.

And oftentimes, this causes a Machine Learning practitioners some problems like underfitting, & overfitting. We’ll discuss underfitting and how to deal with that any other day but let’s discuss one way to tackle with overfitting today.

What’s Dropout?

There are many techniques that ML practitioners use in order to avoid their models’ overfitting behaviour. …


Deep Learning

A step-by-step guide to distinguish between cats and dogs!

Image for post
Image for post
Photo by Jamie Street on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

According to BarkPost.com, there are like 14 breeds of Dogs and Cats which look the same. So, I thought It would be an interesting project to come up with a model that successfully classifies between them.

Cats and Dogs — https://barkpost.com/discover/breeds-that-look-like-cats/
Cats and Dogs — https://barkpost.com/discover/breeds-that-look-like-cats/
Picture from noerihito

Overview

The main aim of the project is to distinguish which image contains a dog in it and which one has a cat in it.

It is actually a relatively simple task as compared to:

But, let’s see how the model performs. …


Deep Learning

Classifying between different weather states!

Image for post
Image for post
Photo by NOAA on Unsplash

Stuck behind the paywall? Click here to read the full story with my friend link!

Who doesn’t likes sunsets? But have you ever thought why are they so beautiful? What makes those clouds suddenly appear super pretty? Is it just that beam of light from that giant hot mess? Well, this is post is not to answer that but to try to classify different weather states based on Pictures provided.

Overview

The main aim of this project is to make a model that correctly classifies the weather states on the images it sees.

This seems pretty easy but the main challenge the model will face is that it doesn’t need to learn about the shapes of the objects in the image, i.e. Clouds, etc. Rather it needs to learn about the sky color in the image. But it does also need to learn where the clouds actually represent the Cloudy weather or are just there. …

About

Danyal Jamil

Machine Learning Enthusiast | Quick Learner | Student

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store