AI, ML, DL Introduction

AI, ML, DL introduction
What is AI?
As per investopedia.com :
- Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think
like humans and mimic their actions.
- The term may also be applied to any machine that exhibits traits associated with a human mind such as learning
and problem-solving.
- The ideal characteristic of artificial intelligence is its ability to rationalize and take actions that have the best
chance of achieving a specific goal.
- A subset of artificial intelligence is machine learning, which refers to the concept that computer programs can
automatically learn from and adapt to new data without being assisted by humans.
Categorization of Artificial Intelligence
● Weak artificial intelligence (AI)—also called narrow AI—is a type of artificial intelligence that is limited to a
specific or narrow area.
● Weak AI lacks human consciousness.
● Uses: helps turn big data into usable information by detecting patterns and making predictions, Facebook’s
newsfeed, Amazon’s suggested purchases and Apple’s Siri
● Strong Artificial Intelligence (AI) is a theoretical form of machine intelligence that is equal to human
intelligence. Key characteristics of Strong AI include the ability to reason, solve puzzles, make judgments,
plan, learn, and communicate. It should also have consciousness, objective thoughts, self-awareness,
sentience, and sapience.
● Strong AI is the theoretical next level of artificial intelligence.
Branches / Sub parts of AI
- NLP
- Computer vision
- Knowledge representation
- Automated reasoning
- Machine learning
- Robotics
Applications of Artificial Intelligence ?
Machine Learning (ML)
What is ML?
As per Wikipedia...
Machine learning (ML) is the study of computer algorithms that improve automatically through experience.
Difference between Normal programming and ML program?
Or…
How do you identify when ML is needed?
Ex. of Image classification/ face recognition

What are the sub-parts (Categories) of ML?
Supervised Learning
Ex. Regression and Classification algorithms
Unsupervised Learning
Ex. Density estimation, Clustering, Projecting high-dimensional data into low
dimensions
Reinforcement Learning (RL)
RL is concerned with the problem of finding suitable actions to take in a given
situation in order to maximize a reward.
Here the learning algorithm is not given examples of optimal outputs, in contrast to
supervised learning, but must instead discover them by a process of trial and
error.
Typically there is a sequence of states and actions in which the learning algorithm
is interacting with its environment.
In many cases, the current action not only affects the immediate reward but also
has an impact on the reward at all subsequent time steps.
RL contd..
A general feature of reinforcement learning is the trade-off between exploration,
in which the system tries out new kinds of actions to see how effective they are,
and exploitation, in which the system makes use of actions that are known to
yield a high reward.
Too strong a focus on either exploration or exploitation will yield poor results.
Other such scenarios….?
Deep Learning
● Branch of machine learning that mimics the workings of the human brain in
processing data for use in detecting objects, recognizing speech, translating languages,
and making decisions
Basic Building blocks of DL
1. Neurons: A unit that carry information and pass it to another layer
2. Neural Network : A Neural Network is nothing but a collection of neurons and
hidden Layers.
3. Bias : Bias is an additional parameter along with weight in the Neural Network which is
used to adjust the output along with the weighted sum of the inputs ( X * W) to the
neuron.
4. Weight : Weight is the parameter in a neural network that transforms input data.
Basically we assign a random number for the weights and bias at the starting and
periodically we improve the weights through special concept called Back propagation.
5. Cost Function: It is the sum of individual errors. Its a measure of how good a neural
network is with respect to it’s given training sample and the expected output.
6. Back Propagation: Method of adjusting bias and weights such that the cost will get be
decreasing to minimum using the derivatives of weights and bias.
W(new)=W(old)-n*dL/dW
7. Activation function: An algorithm to generate the output.
8. Learning Rate : Learning Rate is one of the hyper-parameter that controls how much we
are adjusting the weights of our network.
Common DL architectures
● Convolutional Neural Networks(CNN) -Image analytics
● Recurrent Neural Networks(RNN)- NLP
● Long Short Term Memory(LSTM)- Time series forecasting
● Boltzmann Machine- Speech recognition
● Deep Belief Networks- Clustering of images

AI, ML, DL Introduction

Uploaded by

Copyright:

Available Formats

AI, ML, DL Introduction

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

AI, ML, DL Introduction

Uploaded by

Copyright:

Available Formats

AI, ML, DL introduction

Ex. of Image classification/ face recognition

7. Activation function: An algorithm to generate the output.

● Convolutional Neural Networks(CNN) -Image analytics

● Recurrent Neural Networks(RNN)- NLP

● Long Short Term Memory(LSTM)- Time series forecasting

● Boltzmann Machine- Speech recognition

● Deep Belief Networks- Clustering of images

You might also like