x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

Natural Language Generation

The basics of natural language generation (NLG), based on the curriculum of CIS 5300 – and created with a little help from NotebookLM!All episode cover images created with Flux.1-schnell

technology

All Episodes

14:17

Exam Review: Module 12

Natural Language Generation ·

2024/11/16

Module 12

en

19:22

Exam Review: Module 11

Natural Language Generation ·

2024/11/16

Module 11

en

13:20

Exam Review: Module 10

Natural Language Generation ·

2024/11/16

Module 10

en

12:26

Exam Review: Module 9

Natural Language Generation ·

2024/11/16

Module 9

en

20:01

Exam Review: Module 8

Natural Language Generation ·

2024/11/16

Module 8

en

15:12

Exam Review: Module 7

Natural Language Generation ·

2024/11/16

Module 7

en

16:27

Exam Review: Module 6

Natural Language Generation ·

2024/11/16

Module 6

en

15:00

Exam Review: Module 5

Natural Language Generation ·

2024/11/16

Module 5

en

19:00

Exam Review: Module 4

Natural Language Generation ·

2024/11/16

Module 4

en

15:53

Exam Review: Module 3

Natural Language Generation ·

2024/11/16

Exam Review 3

en

24:03

Exam Review: Modules 1-2

Natural Language Generation ·

2024/11/16

Exam Review: Modules 1-2

en

11:18

Object Detection

Natural Language Generation ·

2024/10/05

In this episode, we dive into YOLO (You Only Look Once), a popular and efficient method for object detection in images. YOLO splits an image into a grid, with each cell predicting a set number of bounding boxes. These boxes are characterized by their dimensions, confidence scores (indicating the presence of an object), and class probabilities (predicting the category of the object). We'll explore the network architecture behind YOLO, including its convolutional and fully connected layers, and

en

9:31

Improvements to CNN Learning

Natural Language Generation ·

2024/10/05

In this episode, we explore key techniques used to enhance the learning process of Convolutional Neural Networks (CNNs), focusing on the challenges of vanishing and exploding gradients. These issues can hinder training by either stalling the learning of deeper layers (vanishing gradients) or causing unstable parameter updates (exploding gradients). We'll break down how to overcome these challenges with solutions like cross-entropy loss functions, RELU activation, deep supervision, and batch

en

11:52

Convolutional Neural Networks

Natural Language Generation ·

2024/10/05

In this episode, we dive into the exciting world of image recognition and explore how to teach computers to recognize images using Convolutional Neural Networks (CNNs). We'll break down how CNNs, inspired by the structure of the human brain, use a sequence of convolutional layers to process visual information. You’ll also learn about the back-propagation algorithm, which enables these networks to automatically learn and fine-tune their parameters. Tune in to discover how this powerful algorithm is

en

11:15

Linear Perceptrons

Natural Language Generation ·

2024/10/05

In this episode, we continue our exploration of machine learning algorithms by introducing the basic perceptron model. We’ll break down how this foundational concept works, its implications, and how it can be extended to tackle complex tasks like object recognition. Tune in to discover how perceptrons form the building blocks for modern AI and computer vision systems!

en

17:38

Linear Regression

Natural Language Generation ·

2024/10/05

In this episode, we dive into the concept of linear regression, a key method for modeling the relationship between input and output features. We'll explore how it's used for prediction tasks, like estimating a cat's weight from its photo by learning from a series of images in different poses and comparing them to real-world data. We’ll also introduce important techniques like the Hough transform, gradient descent, and stochastic gradient descent. Join us to uncover how these tools help us make

en

10:13

Image Carving

Natural Language Generation ·

2024/10/05

In this episode, we explore the fascinating technique of image carving, where we remove or replicate pixels along a seam to seamlessly shrink or enlarge an image without distorting the main objects. We’ll break down how this process works, making it look like nothing changed in the picture, and introduce you to dynamic programming—a powerful computer science tool with a unique and visually intuitive application in computer vision. Join us to learn how this technique transforms images while

en

13:15

Image Blending

Natural Language Generation ·

2024/10/05

In this episode, we dive into the art of image blending, where we seamlessly cut and paste objects from one image into the background of another. We’ll explore the techniques that ensure the transferred object blends perfectly, matching the background’s color, lighting, and texture so it appears as if nothing has changed. We’ll also introduce the Poisson Equation and its role in making these edits flawless, using concepts from least squares and linear algebra. Join us to learn how to create seamless

en

7:44

Image Morphing

Natural Language Generation ·

2024/10/05

In this episode, we explore the fascinating world of image morphing—where you can transform your face into a cat's and even create a hybrid "mean face" that's part you, part cat! We'll dive into the concept of barycentric deformation and learn how to create smooth, parameterized transformations using just a few control points. Tune in to discover the techniques behind blending and morphing images in creative and surprising ways!

en

8:50

Optical Flow Estimation

Natural Language Generation ·

2024/10/05

In this episode, we dive into the world of visual motion and how to compute pixel-level displacement between two images, a process known as optical flow. We'll explore how visual motion is key to tracking objects and plays a crucial role in technologies like self-flying drones and self-driving cars, helping them navigate and understand their environments. Join us as we break down the science behind motion detection and its real-world applications!

en

44 results

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs