Deep Learning With TensorFlow & Keras

Go from beginner to mastery in Neural Networks with OpenCV’s new course offering.

Standard Retail Price: $699

Dear Future Deep Learning Expert,

You are going to be in high demand soon!

OpenCV’s latest course offering, Deep Learning With TensorFlow & Keras, has the potential to sweep your career off its feet and make you the top problem-solving AI technologist in the world.

As indeed.com touted Machine Learning and Deep Learning jobs as the #1 Best Job in US in 2019, the demand for AI talent is growing exponentially.

Be it intelligent robots and factories, automated vehicles, visual surveillance, medical diagnosis and healthcare, fighting climate change or helping the visually impaired, this course will empower your career to take a leap into the awesome field of Machine Learning and Deep Learning.

It’s safe to say that this course will turn out to be the love of your life.

So, if you are excited to get in-depth knowledge about Computer Vision, Neural Networks, Machine Learning and Deep Learning, show us your support by backing us right away!

All backers of our course ‘Deep Learning With TensorFlow & Keras’, the ‘Deep Learning Bundle’ and the ‘CV Master Combo’ will receive a complimentary copy of the ‘Deep Learning With Python’ book by François Chollet.

We create software, hardware and courses for the AI community. Millions of people have used and loved our products. On Kickstarter, we previously raised more than USD 700,000 for our courses. In addition, we have done two campaigns for our hardware platform that surpassed a million $ each. We accomplished this with the help of more than 17000 generous backers.

We are amongst the most trusted names in Computer Vision.

We are OpenCV.

OpenCV is the largest and the most popular Computer Vision library in the world, and has been around for more than 22 years. It is utilized by thousands of companies, products and devices, and is tested for scalability and performance every single day.

We, at OpenCV.org, are on a mission to educate a global AI workforce. We have been offering comprehensive online courses in Computer Vision to professionals, job-seekers and enthusiasts from over 100 countries.

We take great pride in each and everyone who completes our courses successfully. Upon completion of this course, we will award you with a digital certificate from OpenCV.org. You can showcase it across your social profiles, and give a kickstart to your career and continued studies in the field of Computer Vision.

In this course, we will start with a theoretical understanding of Machine Learning and Optimization, and gradually move on to Deep Neural Networks and Convolutional Neural Networks.

Not only will we go over state-of-the-art model architectures used for solving various Computer Vision problems, we will also go over practical considerations needed to successfully train Deep Neural Networks. These include how to prepare datasets, how to perform sanity-checks before embarking on training that can take hours, how to use visualization tools to debug the training process, what workflows to use when the results are not satisfactory, and finally move on to advanced problems like Object Detection, Image Segmentation, and Pose Estimation.

You will be receiving downloadable study materials in the form of Jupyter Notebooks and Python scripts. All Jupyter Notebooks also run seamlessly on free cloud platforms like Google Colab and Kaggle Kernels.

You will have an amazing hands-on experience with ample practice lessons, solved projects, graded quizzes, assignments and projects.

Evolution and history of AI
AI jargon, applications, problem formulation
Supervised learning problems like Regression and Classification
NumPy crash course
TensorFlow & Keras overview
Keras Sequential and Functional APIs
TensorFlow low-level APIs

Gradient-based optimization techniques in ML
Mathematical foundation for Regression and Classification
Implementing a single Neuron to model Linear Regression
Implementing a single Neuron to model Binary Classification

Understanding the role of various layers
Building multi-layer Neural Networks in TensorFlow & Keras
Understanding and implementing building blocks like different Activation Functions, Loss Functions and Hidden Layers
Understanding and implementing Backpropagation

Deep diving into Convolutional Neural Networks (CNN) and their building blocks viz. Convolution and Pooling
Teaching computers to differentiate between objects using Image Classifiers
Understanding and implementing state-of-the-art models like ResNet, MobileNet, and EfficientNet
Building custom models from scratch
Implementing Transfer Learning and Fine Tuning to build models on custom data
Building Image Classifiers using custom data like Sign Language Classifier, Fruits Classifier and Type of Sport Classifier

Understanding issues with training Deep Networks
Improving generalization capabilities of models with Regularization techniques like Dropout and Batch Normalization
Adding robustness with Data Augmentation
Getting insights with visualization tools like TensorBoard
Using and choosing better Optimizers
Advanced training using Learning Rate Schedulers
Using Callbacks in Keras for monitoring and tracking experiments like Early Stopping and Checkpointing
Implementing Optimizers from scratch

Building a custom Object Detection model to detect safety kits at construction sites
Evolution from traditional Object Detection algorithms to state-of-the-art Deep Learning-based methods
Using the TensorFlow Object Detection API
Problem formulation, custom layers and loss functions used in Object Detection such as Anchors, NMS, IoU, etc.
2-stage and 1-stage object detectors
Learning about Object Detection models like RCNN, SSD, RetinaNet, YOLO, EfficientDet

Building a Semantic Segmentation model for identifying objects in underwater imagery
Problem formulation, custom layers and loss functions associated with Segmentation such as Dilated and Transposed Convolution, Dice Loss, Pixel Accuracy, etc.
Learning about Semantic Segmentation methods like DeepLab v3, FCN and UNet
Learning about Instance Segmentation models like Mask-RCNN
Learning to build custom Segmentation models of your own choice with your own data

Understanding how state-of-the-art algorithms for Pose Estimation work and use them to solve real-world problems

One of the top 30 AI influencers to follow on Twitter as per IBM Watson blog (2017)
Alumnus of Indian Institute of Technology (IIT), Kharagpur and Ph.D. from the University of California (San Diego)
Author of Computer Vision blog LearnOpenCV.com
Work featured in publications such as BBC, Time, Huffington Post, Wall Street Journal, Oprah Magazine, TechCrunch and TheRegister.co.uk

BS from University of California, Berkeley and Ph.D. from Boston University in AI, Machine Learning and Neuro-Modelling
Served as a Visiting Professor at Computer Science Department, Stanford University for 7 years
Founder of the most powerful and popular Computer Vision library in the world, OpenCV.org
Organized the Computer Vision team for Stanley, the autonomous car that won the $2M DARPA Grand Challenge and currently displayed at the Smithsonian Air and Space Museum

Ph.D. in Computer Science from the University of South Florida
Pioneered the development of automated systems for the Deaf community, helping them sign and communicate with others by translating American Sign Language to English text
Published multiple research papers in top scientific conferences including IEEE Conference on Computer Vision and Pattern Recognition, and high-impact scientific journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence

AI & Computer Vision Researcher and an Alumnus of Indian Institute of Science (IISc), Bangalore
Leading planning and development of our Computer Vision and AI courses, in partnership with OpenCV
Over a decade of rich experience as Professor, AI Engineer and Data Scientist
Worked on various Deep Learning and Computer Vision projects with Samsung and Snapdeal
Interested in doing research in the field of Machine Perception, Scene Understanding, Deep Learning and Robotics

Masters degree in Aeronautics and Astronautics from Massachusetts Institute of Technology (MIT), including graduate course work in Machine Learning and Image Processing at Stanford University
Extensive experience in the space science and defense industries, supporting several major development programs and research efforts for over two decades
Background in modelling and simulations, satellite systems, orbital analysis and machine learning

Risks and challenges

Our risk assessment to roll out the product is LOW with HIGH DEGREE of DELIVERY CONFIDENCE in May 2022. We have completed the course design and are in the advanced stages of development. We have a strong track record of successfully delivering AI, Computer Vision and Deep Learning courses. AI professionals and enthusiasts from more than 100 countries have benefited from our courses. Our course instructors are truly world-class with exceptional credentials in AI and Computer Vision research, education and consulting.