LEARNING

Presented by-
Debashis Biswas
Manmohan kumar
Aditya Agrawal
Sourabh kumar Singh
Sabhyasachi Dey
Vivekanand Gond
 Learning

• Learning is (relatively) permanent change in

behaviour as the result of experience.
• It is acquiring new or modifying existing
knowledge, behaviours, skills, values, or
preferences and may involve synthesizing
different types of information. The ability to
learn is possessed by humans, animals and
some machines.
 Why learning occurs?
Human learning may occur as part of
education, personal development, or training.
It may be goal-oriented and may be aided by
motivation. The study of how learning occurs
is part of neuropsychology, educational
psychology, learning theory, and pedagogy.
 Theories Of learning
• Behavioural

Classical conditioning
Operant conditioning

• Cognitive

Social learning
 Classical conditioning

A type of conditioning in which an individual

responds to some stimulus that would not
ordinarily produce such as response.
 Experiment of Ivan Pavlov

Presentation of food Salivation response

Before conditioning
 Experiment of Ivan Pavlov

Presentation of food Salivation response

Sound of bell

During conditioning
 Experiment of Ivan Pavlov

Sound of bell Salivation response

After conditioning
 Operant Conditioning
• A type of conditioning in which desired
voluntary behaviour leads to reward or
prevents a punishment.

• Consequences determine the behaviour that

results in learning.
 Operant Conditioning
• B.F. Skinner- Skinner Box
 Operant Conditioning

Types of reinforcement

- Positive reinforcement

- Negative reinforcement
 Operant Conditioning

Schedules of reinforcement
. Continuous
• Fixed interval
• Variable interval
• Fixed ratio
• Variable ratio
 Schedule of reinforcement
Reinforcement Nature of Effects of Example
schedules reinforcement reinforcement

continuous Reward given after each Fast learning of new Compliments

desired behaviour behaviour but rapid
extinction

Fixed- Reward given at fixed Average and irregular Weekly pay checks
time intervals performance with rapid
Interval extinction

Variable Reward given at variable Moderately high and Pop quizzes

time interval stable performance with
Interval slow extinction

Fixed Ratio Reward given at fixed High and stable Piece-rate pay
amount of output performance attained
quickly but also with rapid
extinction
Variable Ratio Reward given at variable Very high performance Commissioned sales
amount of out put with slow extinction
 Social learning Theory
• The view that people can learn through
observation and direct experience.

• Learning occurs by modelling the behaviour of

others.
Facilitation theory (the humanist
approach)
Carl Rogers and others have developed the
theory of facilitative learning. The basic
premise of this theory is that learning will
occur by the educator acting as a facilitator,
that is by establishing an atmosphere in which
learners feel comfortable to consider new ideas
and are not threatened by external factors.
 Holistic learning theory
The basic premise of this theory is that the
'individual personality consists of many
elements ... specifically ... the intellect,
emotions, the body impulse (or desire),
intuition and imagination that all require
activation if learning is to be more effective.
Various research topics on learning
Learning to Integrate
When different perceptual signals of the same physical property are
integrated, e.g., an objects’ size, which can be seen and felt, they
form a more reliable sensory estimate (e.g., Ernst & Banks, 2002).
This however implies that the sensory system already knows which
signals belong together and how they relate. In other words, the
system has to know the mapping between the signals. Can such a
mapping between two arbitrary sensory signals from vision and
touch be learned from their statistical co-occurrence such that they
become integrated? in general, how adaptive is human multisensory
integration and what are the conditions under which it will occur?
 Statistical Determinants of
Visuomotor Adaptation
Rapid reaching to a target is generally accurate, but contains random and
systematic error. Random error is due to noise in visual measurement,
motor planning, and reach execution. Systematic error is caused by
systematic changes in the mapping between the visual estimate of target
location and the reach endpoint. Systematic errors occur, for example, when
the visual image is distorted by new spectacles or when the reach is
affected by external forces on the arm. Humans minimize systematic errors
(i.e., maintain accurate reaching) by recalibrating the visuomotor system.
We investigated how different sorts of error affect recalibration rate by
manipulating the statistical properties of systematic error and the reliability
with which the error could be measured. We modelled the process using an
optimal predictive filter- the Kalman filter. Model and human behaviour was
similar: less reliable measurements decreased recalibration rate; more
variation in systematic error caused an increase.
 Perceptual learning
Here we investigate perceptual learning in the broad
sense. Generally perceptual learning is understood as
the improvement in performance of a perceptual task
due to prolonged exposure of the learned signal and/or
training of the task. An example would be that we are
better able to discriminate a certain motion direction from
others after training with that specific motion direction.
But perceptual learning incorporates more than just the
improvement or adjustment in the perception of signals
that we are already well aware of.
 Learning cue reliability and
Bayesian priors
To interpret complex and ambiguous input, the
human visual system uses prior knowledge or
assumptions about the world. We show that the
‘light-from-above’ prior, used to extract
information about shape from shading is
modified in response to active experience with
the scene. The resultant adaptation is not
specific to the learned scene but generalizes to
a different task, demonstrating that priors are
constantly adapted by interactive experience
with the environment.
Case Study, Creating a Learning Organization Culture for Skills
Transfer
The Challenge:
• What do you do when your average age is 49 and your
workforce is comprised of highly skilled technical
engineering people? This succession nightmare forced a
Fortune 500 company to take a serious look at preparing
for the future. They called The Adele Lynn Leadership
Group for solutions.
• We knew that the workforce was highly experienced and
independent minded. They prided themselves on
individual contributions. We also knew that they believed
that the “younger generation of engineers” were just not
as motivated and dedicated as they were. We also knew
that the learning curve for the type of work these master
engineers performed was very long.
 The solution:
We knew that the key was to shorten the learning curve AND create
a mindset that allowed the learning to transfer between generations.
We created a formal structured mentoring program, complete with
copious plans for data transfer, progress measurement, and
evaluation. (These were engineers and they valued the structure.)
But, central to the success of the mentoring assignments, we knew
that the very culture of learning had to change or that the mentoring
would fail. We worked with leadership to help the mentors believe
that this contribution was part of their legacy. Then, we worked
extensively to give both the mentors and the mentees the tools they
needed to succeed. These tools included how to build trust in the
relationship, how to transfer learning, how to respect differences in
learning styles, and generational difference that could interfere with
the relationships.
 The Result
Nearly 100 new engineers have been hired and
are in the mentoring process. These engineers
are all assigned mentors and the mentor, the
mentee, and the managers regularly hold
discussions to evaluate the mentoring progress.
The status of mentor has created renewed
enthusiasm for the mentors. Turnover rate for
the new engineers is lower than at any other
time in the last 10 years, and the company is in
the process of developing the talent they need
for the future.