week 1 Flashcards
chp 1
what’s AI? (definition)
A branch of computer science that deals with creating computer
systems or software that can do tasks that usually require human intelligence.
how did AI started?
AI 1950s-1980s :Any technique which enables cp to mimic human behaviours.
ML 1980s-2010: Subset of AI techniques which use statistical methods to enable machines to improve with experiences.
DL 2010-now
Subset of ML which make the computation of multi-layer neural networks feasible.
Domains of AI
1) NN
2)Robotics
3)Expert system
4)CV
5)Speech processing
6)NLP
MACHINE LEARNING:
THE ENGINE
POWERING AI
Machine learning is a subfield of AI
that enables machines to learn from
data without being explicitly
programmed. It is the key technology behind many
AI applications.
How Human and
Machine Learns?
Similarities
* Learn
* Experience
* Feedback
Differences
* General vs. specific learning
* Small vs. big data
* Learning speed
ML MODELS
Supervised
Learning
-Learn from
labeled data
-Decision Tree,
Support Vector
Machine
Unsupervised
Learning
-Learn from
unlabeled data
-K-Means Clustering
Reinforcement
Learning
-Learn to make
decision through
reward by
continuous trial
and error
-Markov decision
Process
TYPES OF SUPERVISED LEARNING
Classification
*It involves a type of problem
where the output variable is a category or categorical such as “positive or negative”, “living things or non living things”.
Problems that involve predicting a
category output:
● Image classification
○ Medical image classification
● Text classification
○ Sentiment analysis
○ Spam detection
Regression
*It involves a type of problem
where the output variable is a real value or quantitative such as weight, budget, etc.
Predicting stock price
● Predicting a house’s sale
price based on its square
footage
● Revenue forecasting
WHAT IS DEEP LEARNING?
- One of the machine learning technique that learns features
directly from data (automatic features extraction). - Deep learning performance improve tremendously when trained
on more data
AI VS ML VS DL
Development of smart systems & machines that can carry out tasks that typically require human intelligence vs Creates algorithms that can learn from data and make decisions based on patterns observed require human intervention when decision is incorrect vs uses an ANN to reach accurate conclusions without human intervention
UNDERSTANDING GENERATIVE AI (definition)
Generative AI is a subset of AI that’s designed to create new, original content. It can generate text, images, music, videos, and even data that resembles or is entirely indistinguishable from
human-generated content.
UNDERSTANDING GENERATIVE AI (How it works)
Generative AI models learn patterns from input data and then generate new content based on that learned information. These models often use advanced techniques such as neural
networks and deep learning.
AI: REVOLUTIONIZING INDUSTRIES
Healthcare : Analyze medical data, provide better diagnoses, recommend
Finance : Detect fraud, predict stock prices, automate financial process
Education: Personalize learning, identify at-risk students, interactive
Transportation: Autonomous vehicle, optimize logistic, reduce traffic congestion
Customer service: Automate customer support, improve service satisfaction
Choose one of the following
domains—Healthcare, Transportation,
Finance, Retail, Manufacturing, or
Agriculture—and describe how AI is
transforming the industry. Provide one
specific example of an AI application
in the chosen domain and explain its
impact on efficiency, accuracy, or
overall outcomes
Domain Healthcare:
AI is revolutionizing healthcare by enhancing diagnostics, personalizing treatment plans, optimizing hospital operations, and facilitating drug discovery. Through the use of machine learning, natural language processing, and computer vision, AI systems can analyze vast amounts of medical data more quickly and accurately than humans, leading to improved patient outcomes.
Specific Example: AI in Medical Imaging
One transformative AI application in healthcare is the use of deep learning algorithms in medical imaging diagnostics. Tools like Google’s DeepMind and Zebra Medical Vision leverage AI to detect anomalies in X-rays, CT scans, and MRIs. For instance, AI systems can identify early signs of diseases such as cancer, fractures, or neurological disorders with high precision.
Impact:
Efficiency: These systems significantly reduce the time radiologists spend reviewing images. An AI can scan hundreds of images in seconds, compared to the hours it might take for a human.
Accuracy: AI-powered tools often outperform human radiologists in detecting subtle patterns that indicate diseases. For example, they have shown higher sensitivity in detecting breast cancer from mammograms.
Outcomes: Early and accurate detection allows for timely interventions, reducing morbidity and mortality rates. Hospitals using such systems have reported faster diagnosis turnaround times and improved patient satisfaction.
