2. 2
Content 目 录
Introduction About AI
What Is The Machine Learing (ML)
Different Types of Machine Learning
comparison Between ML and DL
Conclousion
What Is the Deep learning (DL)
4. TEACH A COURSE 4
What Is Machine Learning
Machine Learning is the general term for when computers learn from data. It
describes the intersection of computer science and statistics where algorithms
are used to perform a specific task without being explicitly programmed; instead,
they recognize patterns in the data and make predictions once new data arrives.
6. TEACH A COURSE 6
Different Types of Machine Learning
Supervised learning
‘’Task driven’’
• to oversea or direct a certain activity and make sure it's
done correctly.
• This type of learning the machine learns under guidance.
• by feeding label data and explicitly telling him this is the
input and that how the output must be.
7. TEACH A COURSE 7
Different Types of Machine Learning
Unsupervised learning
‘’Data driven’’
• means to act without anyone’s supervision or direction
• data not labeled there is no guide and machine have to figure out
the data set given to find hidden patterns in order to make
predictions about the output
8. TEACH A COURSE 8
Different Types of Machine Learning
Reinforcement learning
‘’Learn from errors’’
• learining from experiance , by producing actions and
discovers errors or rewaeds
• once trained it gets ready to predict the new data
presented to do it by itself.
9. What is Deep Learning?
• Deep learning is a subfield of machine learning. It analyzes data logically and can take place
through both supervised and unsupervised learning.
• Deep learning applications are inspired by the working of the human brain. They use
artificial neural networks (ANN), a layered structure of algorithms.
• It can be used for various tasks like natural language processing, image and speech
recognition, and decision-making.
10. TEACH A COURSE 10
Different Types of Deep Learning
• Artificial Neural Networks (ANN)
This type of neural system — patterned around how neurons work in
our brain — recognizes patterns in raw data, helping solve complex
processes.
• Convolution Neural Networks(CNN)
Convolution Neural Networks are mainly credited for their role in image
and video recognition, recommendation systems, and image analysis
and classification.
• Recurrent Neural Networks (RNN)
RNNs are unique on account of their ability to process both past data
and input data — and memorize things — and were developed to
overcome the weaknesses of the feed-forward network. Practical
applications include Google’s voice search and Apple's Siri.
11. TEACH A COURSE 11
comparison Between ML and DL
Maachine learning Deep learning
It is a subset of Artificial Intelligence. It is a subset of Machine Learning.
It uses structured data. It uses artificial neural networks (ANN).
It does not require huge data points. It requires millions of data points.
It uses automated algorithms to predict
future actions.
It uses ANN to pass data through
processing layers.
It learns from past data to make future
predictions.
It resolves various machine-learning
issues.
Its training is done by using the Central
Processing Unit (CPU).
Its training is done by using Graphics
Processing Unit (GPU).
Human intervention is needed to get the
required outcomes.
It is self-reliant.
The ML model can resolve easy and a
little bit complicated issues.
Deep learning models can resolve very
challenging issues.
12. TEACH A COURSE 12
How Is Deep Learning Related to Machine Learning?
• Deep learning is a part of machine learning.
• It is a type of machine learning that employs different neural networks to learn data
representations. It uses neural networks to learn complex patterns in data. While that is the
case, machine learning embodies various methods for coaching models to make forecasts or
choices based on information.
• Natural Language Processing (NLP), that deals with enabling machines to interpret and
understand digital images and videos.
• Both machine learning and deep learning belong to the same platform, i.e., Artificial
Intelligence. Both of them can perform tasks like image recognition and speech recognition.
13. 13
Conclusion
• Both machine learning and deep learning can positively influence a lot of
technological advancements in various fields.
• The choice between deep learning and machine learning depends on
the specific problem, available data, and the resources for training and
deployment.