0% found this document useful (0 votes)
2 views23 pages

4.Machine Learning

The document discusses the application of machine learning in management, highlighting concepts such as supervised and unsupervised learning, model building, and the significance of neural networks inspired by cognitive neuroscience. It covers various neural network architectures including feedforward, convolutional, and recurrent networks, as well as the evolution of large language models in generative AI. Key techniques like back propagation and gradient descent are also explained in the context of training neural networks.

Uploaded by

faizul ahamed
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
2 views23 pages

4.Machine Learning

The document discusses the application of machine learning in management, highlighting concepts such as supervised and unsupervised learning, model building, and the significance of neural networks inspired by cognitive neuroscience. It covers various neural network architectures including feedforward, convolutional, and recurrent networks, as well as the evolution of large language models in generative AI. Key techniques like back propagation and gradient descent are also explained in the context of training neural networks.

Uploaded by

faizul ahamed
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

AI for Management

Machine Learning
Saji K Mathew, PhD
Professor, Management Studies
INDIAN INSTITUTE OF TECHNOLOGY MADRAS
Learning algorithms
 If a machine could engage in conversation
indistinguishable from a human, it could be considered
intelligent—Alan Turing
 Turing test was designed to provide a practical method
for evaluating machine intelligence
Explanatory vs predictive modeling
Machine Learning (ML)
 In supervised learning, for each observation of the
predictor measurement(s) xi, i = 1, . . . , n there is an
associated response measurement yi. It uses labelled
data
 Eg.: regression,
 In unsupervised learning, for every observation i = 1, .
. . , n, we observe a vector of measurements xi but no
associated response yi.
 Eg.: clustering
 Statistical vs algorithmic
 Two different knowledge communities
 Black box vs white box models
 Model interpretability and explainability
Model building
Suppose that we observe a quantitative response Y and p
different predictors, X1,X2, . . .,Xp. We assume that there is
some relationship between Y and X = (X1,X2, . . .,Xp), which
can be written in the very general form
Y = f(X) +
Statistical learning refers to a set of approaches for
estimating f
Training: Residual Sum of Squares,
Choice of models: prediction error-
flexibility (bias-variance) trade off

 LHS: Different fits (linear regression (orange)


 RHS: Red Line: Test MSE, Grey line: Training MSE
Cognitive neuroscience: Understanding
the brain
 Deals with mental abilities and brain functioning
 Invention of microscope, and neurons thereafter
 Neurons as fundamental elements for brain’s information
processing
 Neuron-neuron communication through release of
neurotransmitters (chemicals) into junctions between
neurons (synapse)
 An average brain has ~100bn neurons, each one
connected to 15,000 other neurons
 When one neuron fires another, it becomes a Hebbian
circuit (neurons that fire together, wire together)
 the concept of Hebbian learning (1949)
The neuron
Artificial neural networks are inspired by the architecture of
the human brain.
The idea of artificial neuron
[Link]
to-redeem-the-world-with-logic-
235253/
The Perceptron (Rosenblatt, 1957)
Towards back propagation
 Perceptron training may not converge if the linear unit
is not linearly separable
 Marvin Minsky vs Frank Rosenblatt debate
([Link]
debates/minsky-vs-rosenblatt
 Solution: Back propagation algorithm, a method for
training neural nets devised by researchers in the 60s,
was revisited by Rumelhart, Hinton, and Williams;
they published a paper, which outlined a clear and
concise formulation for the technique and it paved its
way into the mainstream of machine learning research
(Rumelhart et al. 1986).
BP algorithm

is half the squared difference between the target output td and the linear
unit output od, summed over all training tuples.

Here E is a function of weight vector, it is dependent on the linear unit output


(od).
Gradient descent search determines
a weight vector (partial differentials)
that minimizes E
Starts with an initial weight vector and
modifies it in steps
At each step the weight vector is altered
In the direction that produces steepest
descent along the error surface
A case: feedforward ANN training for
prediction
Target

Compare
Feed-Forward Neural N/w topologies
ANN learning models
 Feedforward, back propagation
 Limitation: vanishing gradient problem, 2-3 hidden layers
 Applications: forecasting, classification
 Convolutional Neural Networks (CNN)
 Convolution”—working and reworking the original input, by
pooling data across layers; can have thousands of layers,
computationally expensive
 Applications: image recognition
 Recurrent Neural Networks (RNN)
 Prior inputs to influence the current input and output
(feedback), effective in speech recognition and timeseries’
reinforcement learning takes human/machine feedback
 Deep learning with transformer architecture
 State of the art, thousands of layers, used in GenAI
[Link]
The cusp: Large Language Models (LLM)
 Foundation of Generative AI, which generates new content
 ChatGPT, DALL-E
 Stochastic parrots? (lacks in connection, composition)
 Hallucination/confabulation
Evolution of LLM
 Bag of words to semantic meaning through Word2Vec
(Mikolov et al. 2013)
 Transformer architecture and deep learning (“Attention is all
you need”: Vaswani et al. 2017; Wei et al. 2022)
 Overcomes the limitation of BP algorithm for ANN training
Word embedding
 Distance between words based on semantics
The transformer

[Link]
[Link]
LLM gallop

You might also like