The skill set  gained after attending the workshop is called learning outcomes. We set six learning goals for the workshop. They are,

 you will be able to:

• Define the process of learning and how to measure it for any learning models. Understand the difference between Machine Learning and deep learning.

• Preparing the data required for training and testing the model.

• Understand the convex optimization and loss functions and know how  learning actually takes place in the model.

• Code a single neuron from the scratch  and understand over fitting, under fitting and regularization.

• Code DNN (Deep Neural Network) using python framework and understand the vanishing gradient problem and need to choose different activation functions.

• Code CNN (Convolutional Neural Network) using python framework. 

1.Introduction to learning  

                                 A brief and quick overview on the history  and recent trends in deep learning era.  Having said that, we define the principle of learning  and show how large amount of data guarantee an exponential  improvement in the performance  of a learning model. In addition to that we discuss about various learning strategies in the absence of sufficient data and learn the difference between machine learning and deep learning.

2.  Setting up the Coding Environment  

                The are plenty of programming languages available , but we choose python for its elegance. There are many ways to setup the environment with the required libraries to execute the code.  And also there are many IDEs available to write the python script. All of them are fine!. We choose Anaconda python package manager for the beginners because of its simplicity in installing it (So we can save our time) and ability to create a virtual environment within the conda environment.  Having installed the Anaconda, we will discuss as well as install required python packages to develop the deep learning models.

[ We preinstall everything and make the system ready for you to code directly. However, if you bring your personal system this session would help you to install those packages in your system].

3. Data set Preparation

                  It is often said in deep learning community that, on average , 70 % of the  project time  will be spend on  preparing ,undertanding and pre-processing the data  to make it suitable for the model. Of course, this is in fact true in our own experience as well.  So, having solid understanding of the data often helps us to solve the problem at hand quickly. Since we use supervised learning models, we spend quite a some time on how to prepare data and label it properly. Subsequently, we discuss about dividing the entire data set into  batches of training, validation and Testing data set. 

4.  Math of Learning Models

             What we often see is that most coder ignore the concept of math while developing models for their problem at hand and struggle a lot latter to debug  the code when they under perform. Learning mathematical component of each block in the deep learning model is as important as breath to body to keep it healthy and alive. Though it is not possible to teach every math concept in detail  in 16 hours,  we endeavor to give you an intuitive idea of  equations involved by considering a single neuron as an example . Once if you glimpse  a beauty of it, you will strive on your own to learn a lot about it over the period of time. We are sure of that!

Math concepts involved :  n-dimensional space (Linear algebra), Function approximation, Optimization using back propagation.

5. Code the Math 

                 Once if you understand the math concepts involved in learning models, code it in python to deepen your understanding.  We create a single neuron to approximate a linear / non-linear functions and explore the concepts of optimization, loss and error surfaces, under fitting, over fitting and regularization. Anything in its simplest form gives us great insights.  The entire deep learning process consists of only two parts : Forward Propagation and Backward Propagation.  If you understand them for a single neuron, you took a giant step forward! Congratulations :-)

6. Deep Neural Networks (DNN) and Vanishing gradient problem.

          Having mastered many concepts with the help of single neuron, now it is time to scale it up to have 'N' neurons. Not only that, we can create a  layered network of neurons. The problems of greater complexity can be solved by such networks.  Unfortunately, scaling up the network doesn't always guarantee a good performance and it also brings us a few obstacles  in the learning process. One such problem is vanishing gradient problem. We discuss those problems and also show you methods to eliminate it by using various activation functions and regularization strategy.

          To code DNN, of course we can start from the scratch using numpy alone, but difficulty lies in coding back propagation part . So it is wise to use some beautiful frameworks such as Tensorflow, Pytorch or Keras (still lot more is there)  which takes care of back propagation part and also runs on GPU.In fact,  the choice of framework doesn't matter at all once if you understand the skeleton of the model. 

Thanks for all those who have attended and benefited out of the workshop. Based on your feedback, we try minimizing math details in the next workshop and give you hands on in python and Numpy prior to coding the DNN and CNN.