Deep Learning in Python

Member Feature Story

The right — and wrong — way to compete with a locked market

"A Breakthrough In Machine Learning, Would be worth ten Microsofts..."

-Bill Gates
Why Linear Algebra Critical to Understand Deep Learning..?


he field of Artificial Intelligence is essentially when machines can do tasks that typically require human intelligence. It encompasses machine learning, where machines can learn by experience and acquire skills without human involvement. Deep learning is a subset of machine learning where artificial neural networks, algorithms inspired by the human brain, learn from large amounts of data.

Similarly to how we learn from experience, the deep learning algorithm would perform a task repeatedly, each time tweaking it a little to improve the outcome.. We refer to ‘deep learning’ because the neural networks have various (deep) layers that enable learning. Just about any problem that requires “thought” to figure out is a problem deep learning can learn to solve.

Why It’s So popular Now a days?

The amount of data we generate every day is staggering—currently estimated at 2.6 quintillion bytes—and it’s the resource that makes deep learning possible.The Neural networks come earlier during but now the cheap computation power and so much data availability make it possible to perform human-level tasks.

We cover deep neural network in our curriculum which are the artificial neural networks based on biological neurons they can learn and combine simple features to make a complex function. Like in following they learn to classify between red and blue dots with simple linear boundaries to make complex, non-linear boundary..

In Deep learning mainly 2 parts came - Computer vision (CNN) - Image recogniton, object detection, activity recognition etc. Natural language processing - text classification, language translation, chatbots etc.

CNN - does take a biological inspiration from the visual cortex. The visual cortex has small regions of cells that are sensitive to specific regions of the visual field, like some neurons fired when exposed to vertical edges and some when shown horizontal or diagonal edges.

A more detailed overview of what CNN's do would be that you take the image, pass it through a series of convolutional, non-linear, pooling (downsampling), and fully connected layers, and get an output.

Don’t be feared from this layers they just feature extractors and make complex decision combining those simple features.

We cover the Computer vision Or Convolution neural networks different Topics -


Beside of recognition we give in-depth knowledge on object detection and segmentation networks like YOLO and their different versions.

We are focused on practical working with the theory of this networks we implement then in Keras, tense flow etc . framework to build something which can show you the real world use cases of computer vision.

There are different architectures we cover from the start to the recent state of the networks - SO
SO actually convolution Networks become so popular when then surpass human-level performance in 2012 Imagenet competition for image recognition taks. We cover mainly these networks in image recognition task - Alex net Vggnet Resnet Densenet etc.