Machine Intelligence is the last invention that humanity will ever need to make🏳. With this belief, :-D GDG Cloud Nagpur is thrilled about its first offline event- ML on Cloud Series: Episode 1🙆‍♀️- Transfer Learning! 🥞in colab with TFUG Nagpur. Know our speaker: Vedant Khairnar,⚡ Organiser @ GDG Cloud Nagpur | Developer Advocate, ⛳CatalogicSW. Venue - Government College of Engineering🏁, Nagpur. :-P When? Saturday, 6th August 2022 at 12:01 PM💁‍♀️, IST. 🍱Deliverables- • Hands-on experience in trending tech. • Amazing swags🏖 for all the participants. 🎲RSVP- https://gdg.community.dev/e/mjy2tf/ If you are a tech enthusiast🧢, you are invited to take the Offline Community Experience!

1. Introduction to
AI
Vedant Khairnar

2. What we need to learn before we start?
◈ Python

3. So let’s brush-up .py!!

4. Artificial
Intelligence
◈ It is said that the term machine
learning was first coined by
Arthur Lee Samuel, a pioneer
in the AI field, in 1959.
◈ Machine learning is the field of
study that gives computers the
ability to learn without being
explicitly programmed. 2 —
Arthur L. Samuel, AI pioneer,
1959 .

5. What’s new
now?

6. Applications of AI
◈ Email spam detection
◈ Face detection and matching (e.g., iPhone X)
◈ Web search (e.g., DuckDuckGo, Bing, Google)
◈ Sports predictions • Post office (e.g., sorting letters by zip codes)
◈ ATMs (e.g., reading checks)
◈ Credit card fraud • Stock predictions
◈ Smart assistants (Apple Siri, Amazon Alexa, . . . )
◈ Product recommendations (e.g., Netflix, Amazon)
◈ Self-driving cars (e.g., Uber, Tesla)
◈ Language translation (Google translate)
◈ Sentiment analysis
◈ Drug design
◈ Medical diagnose

7. Categories of Machine Learning
◈ Supervised Learning
◈ Unsupervised Learning
◈ Reinforcement Learning
◈ Semi Supervised Learning

8. Supervised Learning
◈ It is the subcategory of machine learning that focuses on learning a classification or
regression model, that is, learning from labeled training data (i.e., inputs that also
contain the desired outputs
or targets; basically, “examples” of what we want
to predict).
◈ Key points:
� Labelled Data
� Direct feedback
� Predict outcome/future

9. Unsupervised Learning
◈ In contrast to supervised learning, unsupervised learning is a branch of
machine learning that is concerned with unlabeled data. Common tasks in
unsupervised learning are clustering analysis
(assigning group memberships) and dimensionality
reduction (compressing data onto a
lower-dimensional subspace or manifold).
◈ Key points:
� No labels/targets
� No feedback
� Find hidden structure in data

10. Reinforcement learning
◈ Reinforcement is the process of learning from rewards while performing a
series of actions.
◈ Typical applications of reinforcement learning
involve playing games (chess, Go) and
some form of robots, e.g., drones, warehouse
robots, and more recently self-driving cars.
◈ Key points:
� Decision process
� Reward system
� Learn series of actions

11. Semi-supervised Learning
◈ Loosely speaking, semi-supervised learning can be described as a mix
between supervised and unsupervised learning. In semi-supervised learning
tasks, some training examples contain outputs, but some do not. We then
use the labeled training subset to label the unlabeled portion of the training
set, which we then also utilize for model training.

12. Title Lorem Ipsum
Lorem Ipsum
Dolor Sit Amet
Consectetuer Elit
Nunc Viverra
Lorem Ipsum
Dolor Sit Amet
Consectetuer Elit
Nunc Viverra
Lorem Ipsum
Dolor Sit Amet
Consectetuer Elit
Nunc Viverra

13. - GCP
- Transfer Learning
- Monk AI
Vedant Khairnar

14. The
difference

15. What is Transfer Learning?
◈ Transfer learning is the idea of overcoming the isolated learning paradigm
and utilizing knowledge acquired for one task to solve related ones.
◈ Situation where what has been learned in one setting is exploited to
improve generalization in another setting.

16. Understanding
Transfer Learning:
Transfer learning is the idea of
overcoming the isolated learning
paradigm and utilizing knowledge
acquired for one task to solve related
ones.

17. Analogy
◈ Know how to ride a motorbike �
Learn how to ride a car
◈ Know how to play classic piano �
Learn how to play jazz piano
◈ Know math and statistics � Learn
machine learning

19. What is Monk AI?
? Low Code Deep Learning
? Compare Experiments
? Resume Experiments
? Latest Libraries support like Pytorch, Mcnet, Keras.
? Curated Workflows
? OpenSource

20. ResNet
◈ ResNet, short for Residual Network is a specific type of neural network that was
introduced in 2015 by Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun in
their paper “Deep Residual Learning for Image Recognition”.The ResNet models
were extremely successful which you can guess from the following:
? Won 1st place in the ILSVRC 2015 classification competition with a top-5 error rate of
3.57% (An ensemble model)
? Won the 1st place in ILSVRC and COCO 2015 competition in ImageNet Detection,
ImageNet localization, Coco detection and Coco segmentation.
? Replacing VGG-16 layers in Faster R-CNN with ResNet-101. They observed relative
improvements of 28%
? Efficiently trained networks with 100 layers and 1000 layers also.

21. Residual Block
◈ This problem of training very deep networks has been alleviated with
the introduction of ResNet or residual networks and these Resnets
are made up from Residual Blocks.
◈ The very first thing we notice to be different is that there is a direct
connection which skips some layers(may vary in different models) in
between. This connection is called ’skip connection’ and is the core
of residual blocks. Due to this skip connection, the output of the layer
is not the same now. Without using this skip connection, the input ‘x’
gets multiplied by the weights of the layer followed by adding a bias
term.
◈ Next, this term goes through the activation function, f() and we get
our output as H(x).
◈ H(x)=f( wx + b )
or H(x)=f(x)
Now with the introduction of skip connection, the output is changed to
H(x)=f(x)+x

22. Some Versions of
ResNet
• ResNet50
• ResNet101
• ResNet152
• ResNet50V2
• ResNet101V2
• ResNet152V2
• The primary difference between
ResNetV2 and the original (V1) is
that V2 uses batch normalization
before each weight layer.

23. ResNet 50
in Keras Arguments
◈ include_top: whether to include the fully-connected layer at the top of the network.
◈ weights: one of None (random initialization), ‘Imagenet’ (pre-training on ImageNet), or
the path to the weights file to be loaded.
◈ input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input
for the model.
◈ input_shape: optional shape tuple, only to be specified if include_top is False
(otherwise the input shape has to be (224, 224, 3) (with ‘channels_last’ data format) or
(3, 224, 224) (with ‘channels_first’ data format). It should have exactly 3 inputs
channels, and width and height should be no smaller than 32. E.g. (200, 200, 3) would
be one valid value.
◈ pooling: Optional pooling mode for feature extraction when include_top is False.
◈ None means that the output of the model will be the 4D tensor output of the last
convolutional block.
◈ avg means that global average pooling will be applied to the output of the last
convolutional block, and thus the output of the model will be a 2D tensor.
◈ max means that global max pooling will be applied.
◈ classes: optional number of classes to classify images into, only to be specified if
include_top is True, and if no weights argument is specified.
To implement ResNet version1 with 50
layers (ResNet 50), we simply use the
function from Keras as shown below:

24. Classification
Transfer learning: Take a model
trained on a large dataset and transfer
its knowledge to a smaller dataset.
METHODOLOGY
Monk AI: Monk is a low code Deep Learning tool
and a unified wrapper for Computer Vision.
1. Finding a dataset on
Kaggle.
2. Deciding the Pre-trained
Neural Network Model to
use.
3. Training and hypertuning
on the new dataset.
4. Testing on the test
dataset.

25. It’s Demo Time!!
Enough of theory!

26. Any Questions?

27. Vedant Khairnar