Deep Learning for Professionals

Name: Deep Learning for Professionals
Rating: 1.7 (3 reviews)

Learn the fundamentals of deep learning using real world solutions

Created byEduonix Learning Solutions

Last updated 11/2022

English

English [Auto],

What you'll learn

Learn the core concepts of deep Learning
Learn the structure of deep learning algorithms
Learn to build deep learning pipeline using Python and Tensorflow
Implement a neural network solution from ground up

Course content

5 sections • 53 lectures • 4h 31m total length

Course Introduction0:58
Explore the deep learning pipeline with TensorFlow and Python, and study the ingredients for a deep learning algorithm. Understand neural network design and the structure of deep learning research.

Section Introduction0:44
What is Artificial Intelligence?5:09
Ethical Implications of Artificial Intelligence5:05
Introduction to Machine Learning8:13
Types of Machine Learning7:33
What is Deep Learning?5:58
Deep Learning - Real World Applications5:39
Hardware Requirement4:42
Resources for Project4:43
Visualize Neural Networks7:50
Explore visualizing neural networks and deep learning, using a classification dataset of blue and yellow dots, exploring hidden layers, epochs, and training versus test data.
Summary1:04
Quiz

Section Introduction1:37
Probability in Deep Learning4:47
Explore core probability concepts used in deep learning, including random variables, discrete and continuous values, sampling from distributions, and common distributions like uniform, normal, binomial, multinomial, and Poisson.
Calculus in Deep Learning3:56
Chain Rule in Deep Learning5:06
Math in Neural Network6:02
Partial Derivatives8:26
Bayes Theorem4:10
Visualizing Gradient Descent6:33
Overfitting7:28
Underfitting3:09
Increase model complexity to address underfitting by adding neurons and hidden layers; consider removing data, adding features via feature engineering, and reducing dropout; cross validation is covered next.
Cross Validation4:39
Activation Functions9:07
Implement Gradient Descent9:07
Hyperparameter Tuning - 15:49
Hyperparameter Tuning - 23:30
Explore practical hyperparameter tuning options for deep learning, including basin optimization, randomized search, and manual search, and understand when feature engineering can improve model performance without exhaustive grid search.
Optimizers4:59
Decision Tree8:43
Precision and Recall7:37
Data Cleaning5:14
Principle Component Analysis2:54
Summary0:57
Quiz

Section Introduction0:50
Develop skills in Python programming to explore and analyze data before modeling, prepare for handling big data problems, and deepen your TensorFlow learning in section three.
Introduction to Exploratory Data Analysis5:25
Implementing Exploratory Data Analysis7:52
Handling Missing Values4:33
Features of Exploratory Data Analysis8:23
Introduction to Tensorflow4:45
Different Types of Tensors3:40
Comparing different versions of Tensorflow3:56
Data Augmentation3:46
Implement Image Augmentation8:15
Implement Gradient Tape9:08
Summary0:53
Quiz

Section Introduction0:53
Explore neural network design in the final section of deep learning for professionals, analyzing convolutional neural networks for image processing and residual networks with their distinctive skip connections.
Convolutional Neural Network8:06
Dot Product6:20
Explore the dot product for matrix multiplication in convolutional neural networks, multiplying rows by columns to produce a 2x2 output, with examples using matrices A and B and padding considerations.
Vanishing and Exploding gradients5:16
Residual Neural Networks5:20
Recurrent Neural Networks4:30
Implement Convolutional Neural Network7:28
Summary0:53
Explore neural network architectures such as convolutional neural networks, residual networks, and recurrent networks, and prepare to conduct your own deep learning research and develop your own deep learning algorithms.
Quiz

Requirements

Basic knowledge of Python and machine learning algorithms is required to complete this course

Description

Do you want to accelerate your machine learning career with a new skill?

We brought you the professional course on Deep Learning covering the latest concepts and skills required in the market today.

In this course, you'll learn fundamental concepts of Deep Learning, including various Neural Networks designs and ingredients of deep learning algorithms. This course will help you learn how to implement a deep-learning pipeline using TensorFlow and Python.
Deep learning is a very important aspect of machine learning. Deep learning is used for real-world scenarios such as object recognition, computer vision, image and video processing, text analytics, recommender systems, and other types of classifiers.

Major Topics That This Deep Learning Course Covers!

Introduction to the Structure of a DL Research
Basic Ingredients of a Deep Learning Algorithm
Implementing DL Pipeline in TensorFlow
Deep dive – NN design

Why Should You Learn The Deep Learning?

Deep learning has got approval from all major business functions from customer service to cybersecurity and marketing. It's helping in the new age of personalization, fraud detection, forecasting, and even supply chain optimization.

Perks Of Availing This Program!

Get Well-Structured Content
Step-By-Step Building of Deep Learning Research Structure
Learn From Industry Experts
Get a Certificate of Completion

Join today and be market ready!!

See You In The Class!

Who this course is for:

Anyone who wants to learn real world deep learning will find this course very useful

Deep Learning for Professionals

What you'll learn

Explore related topics

Course content

Course Introduction1 lecture • 1min

Introduction to the Structure of a DL Research11 lectures • 57min

Basic Ingredients of a Deep Learning Algorithm21 lectures • 1hr 54min

Implementing DL Pipeline in TensorFlow12 lectures • 1hr 1min

Deep dive – NN design8 lectures • 39min

Requirements

Description

Who this course is for: