DEEP LEarNiNg

MastEr Class
Day-5
Announcement
Attendance Link will be Available around 7:30 PM
 01
Gradient Descent
Concept
Concept
 Gradient Descent
Optimizer- To minimize the loss function or error term

We start with a random point on the function and

move in the negative direction of the gradient of the
function to reach the local/global minima

Gradient descent algorithm needs,

• we require a Cost function that needs to be

minimized,
• the number of iterations,
• a learning rate to determine the step size at each
iteration while moving towards the minimum,
• partial derivatives for weight & bias to update the
parameters at each iteration,
• and a prediction function
 Steps
• Equation y = 2x^2
• dy/dx = d/dx(2x^2)
= 4x

• Initialize random start point = 3

Precision variable:
• Learning rate = 0.01 calculates the difference between two
consecutive “x” values . If the
• Lets us take 2 Iteration difference between x values from 2
• Iteration-1 consecutive iterations is lesser than
x1 = x0 - (learning rate * gradient) the precision we set, stop the
algorithm !
x1 = 3 – (0.01*4(3))
x1 = 2.88
• Iteration-2
x2 = x1 - (learning rate * gradient)
x2 = 2.88 – (0.01 * 4(2.88))
X2 = 2.7648
 Total Value
₹35000
Deep Learning intern OFFER
₹999
• 30 Day Video Lectures (Value: ₹4,000)

• 15+ Projects (Value: ₹25,000)

• Private Community (Value: ₹2,000)

• Weekly Master Mind (Value: ₹1,000)

• Bonus Task, Assignment (Value ₹1,000)

• Technical Materials (PPT & Mindmap) (Value:

₹2,000)

• Internship E-Certificate
02 Practical
 3 Course @999
• Recorded Video Lectures (Value:₹900)
• Source Code based on Application (Value:₹1000)
• Material PPT & Mindmap (Value:₹200)
• Assignment & Support (Value:₹200)
• 15+ Python & CV Projects (Value:₹2000)
• 3 Internship E-Certificate

Total Value: ₹39,999

Offer Value: ₹2,999
Todays Launch OFFER Price: ₹999
A.I Career Assistance Course Bundle
 A.I Career Assistance Bundle
• Access to 6 Technical Course with 150+ Projects (Value ₹80,000)
• Access to 3 Soft skill & Mindset COURSES (Value ₹5,000)
• 250+ Source Code (Value ₹20,000)
• Technical Materials (PPT & Mindmap) (Value ₹10,000)
•
•
Bonus Task, Assignment (Value ₹10,000)
Forum discussion & Support (Value ₹5,000)
9 Course @2999
• 10+ Industry Level Projects (Value ₹25,000)
• 6 Internship E-Certificate(A.I, ML, DA, DL, CV, Python) (Value unlimited)
• Life Time Community for Job Openings & Other discussions (Value ₹5,000)
• Personal assistance for Resume Validation (Value ₹10,000)
• Validity – 1 YEAR
Total Value ₹1,65,000
@₹2999 only
Deep Learning Terminology - 1

Learning Rate
• Step size at each iteration while moving towards the minimum
• The amount that the weights are updated during training is referred to as
the Learning Rate’
• Positive value, often in the range between 0.0 and 1.0
• The learning rate controls how quickly the model is adapted to the
problem
• Smaller learning rates require more training epochs given the smaller
changes made to the weights each update
• Larger learning rates result in rapid changes and require fewer training
epochs
Deep Learning Terminology - 2
Hyper parameter
• A hyper parameter is a parameter whose value is set before the
learning process begins

• It determines how a network is trained and the structure of the

network

Types
• Dropout
• Activation function
• Learning Rate
• Momentum
• Number of epochs
• Batch size
Deep Learning Terminology - 3
Bias, Variance
• Bias – Assumption made by model to make function
easier to learn
• If average predicted value are far from actual value then
bias is said to be high

• Variance – Variability of model prediction for a given

data point which tells the spread of data called variance
of the model
• Model with high variance very flexible to training data
but it cannot fit accurately on test data
 Short bytes – D4

TWCGO Method - Create Individual Bank account & Split the Income

T-Tax | W-Wealth | C-Charity | G-General | O-Operation

—Money Management
Q&A
Session
 Thanks!
Follow Me on LinkedIn : Link in Description
+91 7305845758
Pantechsolutions.net

Ask Your Friends to Participate on this Event