Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Advanced Deep Learning With TensorFlow

Name: Advanced Deep Learning With TensorFlow
Rating: 4.5 (15 reviews)

Deep Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, LSTM, GRU,TensorFlow

Created byDr B S Satputae

Last updated 4/2022

English

What you'll learn

Artificial Neural Networks, Multilayered Perceptron
Convolutional Neural Networks, Recurrent Neural Networks,LSTM,GRUs
TensorFlow, Keras, Google Colab
Real World Projects and Case Studies

Course content

6 sections • 57 lectures • 8h 42m total length

Logistic Regression and Neuron5:57
Relate logistic regression to a neuron with a sigmoid activation using W^T x plus b, and identify the perceptron as the simplest binary-output neuron trained via stochastic gradient descent.
Multi Layered Perceptron5:24
Deep Neural Network Notations11:02
Explore common deep neural network notations, including data points, feature indices, and weight matrices, and understand fully connected architectures with input, hidden, and output layers.
Training a Single Neuron Model16:39
train a single neuron model with regression by minimizing the loss between y and y_hat, and update weights using gradient descent or stochastic gradient descent with a learning rate.
Training a Multi Layered Perceptron24:42
Memoization9:55
Backpropagation Algorithm18:02
Activation Functions18:18
Vanishing Gradient Problem9:39
Explore the vanishing gradient problem in deep networks, caused by repeatedly multiplying derivatives of sigmoid and tanh activations during backpropagation, hindering training across many layers.
Rectified Linear Unit (ReLU)20:42

Introduction to Convolutional Neural Networks(CNNs)4:33
Convolution Operation7:44
Demonstrates the convolution operation in CNNs by applying a 3x3 kernel to a 6x6 input, performing elementwise multiplication, and summation, then sliding to generate the output.
Edge Detection3:52
Apply convolution with edge-detecting kernels to reveal horizontal and vertical edges, using a Sobel detector and zero normalization to produce a grayscale edge map.
Padding and Strides11:36
Max Pooling3:18
Convolution on RGB Images5:57
Convolution Layer in CNN6:10
CNN Example - LeNet8:05
Data Augmentation3:31
Apply data augmentation to build invariant CNNs that classify objects across orientations while expanding the dataset with transformations such as scaling, flipping, rotation, translation, and noise to improve model tuning.
VGG16 Architecture9:43
Transfer Learning10:48

What is Tensor & TensorFlow?13:26
Introduction to Google Colab4:47
Creating Tensor of Constants12:46
Creating Tensor of Variables6:21
Learn the difference between constants and variables in tensors, showing how constants are immutable and variables unlock mutability by indexing and modifying tensor contents.
Creating Tensor of Random Numbers5:59
Creating Tensor of Zeros and Ones2:02
Creating Tensor from NumPy Arrays2:59
Getting Information from Tensor9:19
Tensor Slicing Part110:37
Tensor Slicing Part24:25
Getting only last column from a Tensor4:28
Learn to extract the last column from a 3d tensor by selecting the final elements along each axis. With start and end positions to include all elements.
Getting only last rows from a Tensor3:54
Learn to extract the last rows from a tensor across multiple dimensions by using slice rules and explicit start and end indices to select the final elements.
Basic Operations on Tensor4:16
Matrix Multiplication Part 16:46
Matrix Multiplication Part 2 - Code2:31
Demonstrates multiplying a 2x2 and a 2x3 matrix in Python, verifying the result against a direct calculation and a TensorFlow operation, then hints at reshaping for mismatched dimensions.
Reshaping a Tensor1:50
Transpose of a Matrix7:03
Learn how to transpose and reshape matrices in TensorFlow, convert between two by three and three by two shapes, and perform matrix multiplication by aligning dimensions.

Linear Regression17:44
Explore linear regression with neural networks by predicting prices from features like bedrooms, bathrooms and parking, using mean squared error and mean absolute error to tune w1, w2, and w0.
Linear Regression Neural Network Architecture8:06
Steps in Modelling in TensorFlow3:24
Define a neural network architecture by selecting the input layer, hidden layers, and output neurons, then compile with a loss function and optimizer and train to learn patterns in TensorFlow.
Building Our First Neural Network Model25:02
Medical Insurance Cost Prediction using Regression30:36

Requirements

No Programming Experience, Basic knowledge of Data Science will be an advantage

Description

This Course simplifies the advanced Deep Learning concepts like Deep Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Long Short Term Memory (LSTM), Gated Recurrent Units(GRU), etc. TensorFlow, Keras, Google Colab, Real World Projects and Case Studies on topics like Regression and Classification have been described in great detail. Advanced Case studies like Self Driving Cars will be discussed in great detail. Currently the course has few case studies.The objective is to include at least 20 real world projects soon.

Case studies on topics like Object detection will also be included. TensorFlow and Keras basics and advanced concepts have been discussed in great detail. The ultimate goal of this course is to make the learner able to solve real world problems using deep learning. After completion of this course the Learner shall also be able to pass the Google TensorFlow Certification Examination which is one of the prestigious Certification. Learner will also get the certificate of completion from Udemy after completing the Course.

After taking this course the learner will be expert in following topics.

a) Theoretical Deep Learning Concepts.

b) Convolutional Neural Networks

c) Long-short term memory

d) Generative Adversarial Networks

e) Encoder- Decoder Models

f) Attention Models

g) Object detection

h) Image Segmentation

i) Transfer Learning

j) Open CV using Python

k) Building and deploying Deep Neural Networks

l) Professional Google Tensor Flow developer

m) Using Google Colab for writing Deep Learning code

n) Python programming for Deep Neural Networks

The Learners are advised to practice the Tensor Flow code as they watch the videos on Programming from this course.

First Few sections have been uploaded, The course is in updation phase and the remaining sections will be added soon.

Who this course is for:

Deep Learning beginners
Students, Professionals, Learners who are curious about Deep Learning

Advanced Deep Learning With TensorFlow

What you'll learn

Explore related topics

Course content

Introduction to Neural Networks and Deep Multi Layered Perceptron10 lectures • 2hr 20min

Convolutional Neural Networks11 lectures • 1hr 15min

LSTM12 lectures • 1hr 39min

Introduction to TensorFlow17 lectures • 1hr 43min

Linear Regression using Neural Networks5 lectures • 1hr 25min

Classification Using Neural Networks2 lectures • 20min

Requirements

Description

Who this course is for: