![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
177 Result(s)
-
Video Segment
ANN Overview
This lecture brings out the importance of ANN by presenting several ANN-based AI models which could never be developed using GOFAI. The lecture also gives you a quick overview of ANN technology and how a trivi...
-
Video Segment
Consolidation
This segment provides the consolidation of your entire learning in this course.
-
Video Segment
ANN Terminology
You will learn ANN terminology in this lesson. I will learn activation, optimization and loss functions. You will understand back propagation and the concept of vanishing and exploding gradients.
-
Video Segment
GAN
This lesson teaches you GAN, Generative Adversarial Network. GAN is used for creating images. You will fully learn how GAN creates images which cannot be said to be fake. You will also understand the variants ...
-
Video Segment
Pre-trained Models
In this lesson, you will learn about many pre-trained models both in text and image domains. You will learn many NLP models, starting from initial Word2Vec to the latest LLMs, Transformer based architectures. ...
-
Video Segment
Computer Vision Applications
This lesson describes a real world project for classifying images. You will learn to create your own customized CNN architecture and also use the pre-trained models for classification. I will show you how to i...
-
Video Segment
Network Architectures
This lecture briefs several types of network architectures like RNN, RBF, CNN, LSTM, and Transformers. It will introduce you to the pre-trained models such as YOLO and LLMs like GPT and ChatGPT.
-
Video Segment
CNN
In this lecture, you will learn an important architecture called CNN used in develo** AI models based on image datasets.
-
Video Segment
RNN & LSTM
What role CNN & GAN played in develo** the field of computer vision, a similar role is played by RNN and LSTM in develo** the field of Natural Language Processing, NLP. Recurrent Neural Networks (RNN) is a...
-
Video Segment
NLP Applications
In this lecture, I will discuss a real project for classifying the news headlines from a huge dataset of 93,000+ news items. I will discuss the text processing first and then three approaches based on transfor...
-
Video Segment
A Quick Solution - MLaaS
This video introduces you to the recent innovation in the field of data science and that is ML as a Service, followed by a quick introduction to the instructor and how he is perfectly poised to deliver this co...
-
Video Segment
Do It Yourself
This video tells you how your approach of classical ML development depends on your data size and type.
-
Video Segment
First Things First
This video tells you how to make your data, be it numeric, text or image, machine understable. It also describes the tools available for data visualization to explore your dataset.
-
Video Segment
Centroid-based Clustering
In this video, you will learn centroid-based clustering. The K-means, K-medoids, K-medians, and K-means++ algorithms fall under this category.
-
Video Segment
Mobile Robot Hardware
This video discusses the hardware components of mobile robots, including drive mechanics, controllers, sensors and the overall system design.
-
Video Segment
Less Efforts with ANN
This video describes fully what all you need in building your own ANN network.
-
Video Segment
Classical Algorithms Overview
This video gives you a birds-view on 1000+ classical algorithms available in the market. It brings out regression, classical algorithms and also bagging and boosting techniques.
-
Video Segment
Distribution-based Clustering
This video covers the distribution-based clustering, which is based on the statistical distribution models. Objects belonging to the same distribution form a cluster. This type of distribution is good at captu...
-
Video Segment
Robot Simulation: Concept, Setup
This video segment explains the concept of robot simulation and gives an introduction to the EyeSim simulation system.
-
Video Segment
Mazes: Exploration
This video segment introduces mazes and their simulation environment format. Iterative (left-hand rule) and recursive algorithms for maze exploration are shown.