RAJ KUMAR GOEL INSTITUTE OF
TECHNOLOGY AND MANAGEMENT
TOPIC : DEEP LEARNING
Submitted by: Submitted to:
Disha singh (1533310023)
Vinay sir
(Asst. prof)
Outline
Machine Learning basics
Introduction to Deep Learning
what is Deep Learning
why is it useful
Neural networks
Training
Applications
Limitations
Future scope
Machine Learning Basics
Machine learning is a field of computer science that gives computers
the ability to learn without being explicitly programmed
Machine Learning
Labeled Data algorithm
Training
Prediction
Learned
Labeled Data Prediction
model
Types of Learning
Supervised Unsupervised Reinforcement learning
class A
class A
Clustering
Classification
ML vs. Deep Learning
Most machine learning methods work well because of human-designed
representations and input features
ML becomes just optimizing weights to best make a final prediction
What is Deep Learning (DL) ?
Deep Learning is the field where the machines learn by themselves
by imitating the human brain. Imitate in the sense, the machines can
perform tasks requiring human intelligence.
https://www.xenonstack.com/blog/static/public/uploads/media/machine-learning-vs-deep-learning.png
Now, let’s understand how?
Human brain can easily differentiate between a cat and a dog.
But how can we make a machine differentiate between a cat
and a dog?
But how can we make a machine differentiate between a cat and
a dog?
We would feed the machine (also called training) with a lot of
images of cats and dogs.
Why is DL useful?
o Manually designed features are often over-specified,
incomplete and take a long time to design and
validate
o Learned Features are easy to adapt, fast to learn
o Deep learning provides a very flexible, (almost?)
universal.
o Can learn both unsupervised and supervised
o Effective end-to-end joint system learning
o Utilize large amounts of training data
Neural Network Intro
Weights
𝒉 = 𝝈(𝐖𝟏 𝒙 + 𝒃𝟏 )
𝒚 = 𝝈(𝑾𝟐 𝒉 + 𝒃𝟐 )
Activation functions
How do we train?
𝒚
4 + 2 = 6 neurons (not counting inputs)
𝒙 [3 x 4] + [4 x 2] = 20 weights
4 + 2 = 6 biases
𝒉 26 learnable parameters
Training
Forward it Back-
Sample Update the
labeled data through the
network, get
propagate network
(batch) the errors weights
predictions
Optimize (min. or max.) objective/cost function 𝑱(𝜽)
Generate error signal that measures difference
between predictions and target values
Use error signal to change the weights and get
more accurate predictions
Subtracting a fraction of the gradient moves you
towards the (local) minimum of the cost function
https://medium.com/@ramrajchandradevan/the-evolution-of-gradient-descend-optimization-algorithm-4106a6702d39
Applications –
Virtual assistants
Translation
Image recognition
Voice recognition
Video surveillance & diagnostics
Data mining
Facial Recognition
Personalized shopping & Entertaining
Pharmaceuticals
Image Coloration (B&W to colored)
Some limitations:
deep learning is a tool, not a solution.
large labeled training size to learn new concepts.
lack of interpretability of the models that are learned.
Future Scope :
Self-driving cars:
Conversational assistants and chat-bots
Games
References
http://web.stanford.edu/class/cs224n
https://www.coursera.org/specializations/deep-learning
https://chrisalbon.com/#Deep-Learning
http://www.asimovinstitute.org/neural-network-zoo
http://cs231n.github.io/optimization-2
https://medium.com/@ramrajchandradevan/the-evolution-of-gradient-descend-optimization-
algorithm-4106a6702d39
https://arimo.com/data-science/2016/bayesian-optimization-hyperparameter-tuning
http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow
http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp
