Sign in

Data science , Machine Learning and Deep Learning enthusiast .


  1. ILSVRC’10
  2. ILSVRC’11
  3. ILSVRC’12 (AlexNet)
  4. ILSVRC’13 (ZFNet)
  5. ILSVRC’14 (VGGNet)
  6. ILSVRC’14 (GoogleNet)
  7. ILSVRC’15 (ResNet)
  • ILSVRC stands for Imagenet Large Scale Visual Recognition Challenge or the Imagenet Challenge .
  • ILSVRC is a challenge which is held annually to allow contenders to classify the images correctly and generate the best possible predictions .



Why CNN ?

  • In Fully Connected Neural Networks any neuron in a given layer is fully connected to all the neurons in the previous layer so it consist of many parameters because of that they are more prone to over fitting.
  • As there is a huge chain of neurons, the model can suffer with a problem of vanishing gradients .
  • What we aim is to get a better Optimization Algorithms, Better Activation Functions, Better Initialisation methods, Better Regularization.
  • If we train DNNs on images with larger dimensions then we get a huge number of parameters which requires a lot of computation power.
  • Apparently…

Need of STL?

When we develop some applications we have to deal with data. The data is a collection of values and for storing the collection of values we need data structures. CPP provides built-in libraries of classes for all these data structures and that collection of classes are called STL (Standard Template Libraries ).

  1. ALgorithms
  2. Containers
  3. Iterators
  • Algorithms are the functions used to perform operations on containers
  • For example :











  • A container is a holder object that stores a collection of other objects. …


Biological Neurons*1Oh53dNdPITVnoOVGCCUFA.png
  • Dendrites are to bring inputs from other neurons or the sensory organs .
  • Synapse are the strength of the interaction between two neuron .
  • Soma is some kind of processing unit it takes all the neuron and does some kind of processing on top of it .

Artificial Neuron


  • MNIST stands for Modified National Institute of Standards and Technology database .
  • MNIST dataset is a set of 70,000 small images of digits handwritten by high school students and employees of the US Cen‐sus Bureau.
  • Each image is labeled with the digit it represents. This set has been stud‐ied so much that it is often called the “Hello World” of Machine Learning: when ever people come up with a new classification algorithm, they are curious to see how it will perform on MNIST. Whenever someone learns Machine Learning, sooner or later they tackle MNIST.
  • The MNIST database contains 60,000 training…


Numpy stands for Numerical Python .Numpy is an open source library which is used for numerical operations with respect to linear algebra and matrices .It is created by Travis Oliphant in 2005 .

  • numpy.sort
  • numpy.argmax
  • numpy.count_nonzero
  • numpy.mat
  • numpy.flip

Function 1 — np.sort

Sorting means putting something in a sequence . Numpy comes with an inbuilt library which will allows us to sort an arrray in ascending order and retrurn us a copy of sorted array without modifying the actual instance .

numpy.sort(a, axis=-1, kind=None, order=None)

In this example the print statement will return the sorted version of an array (arr) along with…


PyTorch is a deep learning library as popular as Tensorflow , helps us to bulid deep learning models . It consist of many inbuilt functions and some of them will be discussed here .

Function 1 :

Concatenates the given sequence of seq tensors in the given dimension. All tensors must either have the same shape (except in the concatenating dimension) or be empty., dim=0, out=None)

In this example we are concatenating two (3,3) dimentional metrics. Here torch.zeros will fill all the values with zeros and torch.randn …

Tanuj Shrivastava

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