Presentation is loading. Please wait.

Presentation is loading. Please wait.

Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay.

Similar presentations


Presentation on theme: "Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay."— Presentation transcript:

1 Applications of Deep Learning and how to get started with implementation of deep learning
Presentation By : Manaswi Advisor : Dr.Chinmay Hegde

2 Application -1 Automatic Colorization of Black and White Images

3 Automatic Machine Translation
Application -2 Automatic Machine Translation

4 Automatic Image Caption Generation
Application -3 Automatic Image Caption Generation

5 All about building your first deep learning model
Tutorials: - Brief than the book we are studying ( has implementation of deep learning on MNIST dataset with Theano) - implementation of deep learning on MNIST dataset with Tensorflow Packages Install Anaconda – contains most of the scientific libraries used in machine learning Numpy, Scipy, matplotlib, scikitlearn ( Install Tensorflow – contains deep learning algorithms, different optimization techniques ( ) And that’s it you are ready to build your first deep learning model.

6 For those who want to get started with python
a decent resource to get started with python

7 Datasets MNIST – Large database of handwritten digit
Caltech Pictures of objects belonging to 101 categories Image Net - 14,197,122 images, pictures of objects belonging to categories MNIST CALTECH-101 IMAGE NET

8 Forums Kaggle community– hundreds of datasets to work with and 536,000 fellow members to help you. ( ) - datasets, research groups, jobs, tutorials everything in one place

9 Results on MNIST dataset:
K-NN: Got accuracy up to 85%, but according to Yann Lecun if some tactics (like one vs all classification) are implemented then we can get accuracy up to 95%

10 Results on MNIST dataset:
Neural Networks Quadratic cost Function: 1 hidden layer,30 neurons,30 epochs, mini batch size=10, learning rate=3 – %accuracy 1 hidden layer,100 neurons,30 epochs, mini batch size=10, learning rate=3 – %accuracy Cross entropy cost function: 1 hidden layer,30 neurons,30 epochs, mini batch size=10, learning rate=0.5 – %accuracy 1 hidden layer,100 neurons,30 epochs, mini batch size=10, learning rate=0.5– %accuracy 1 hidden layer,100 neurons,60 epochs, mini batch size=10, learning rate=0.1, regularization parameter = 5.0 – 98.04%accuracy

11 Results on MNIST dataset:
Convolutional nets: convolutional layer with 20 feature maps, 60 epochs, mini batch size=10, learning rate=0.1 – 99.06% accuracy Bottom line convolutional nets perform better than neural nets and KNN when there is enough data

12 Features learnt by conv nets on MNIST dataset
Whiter blocks mean a smaller typically more negative weight, so the feature map responds less to corresponding input pixels. Darker blocks mean a larger weight, so the feature map responds more to the corresponding input pixels

13 GDXray Dataset

14 Accuracy on GDXray Dataset
Got accuracy of 96% with 2 Convolutional layers (each layer having 5x5 filters, 16 feature maps, 2x2 max pool) followed by fully connected layer (100 neurons) and a Softmax layer

15 Weights learnt by conv nets for GDXray dataset

16 The wonderful and terrifying implications of computers that can learn


Download ppt "Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay."

Similar presentations


Ads by Google