J & J Talk AI

Join us for the final episode of Season 2 on J&J Talk AI, where we're exploring the cutting-edge realm of multimodal vision models and their wide-ranging applications. Multimodal vision models might sound like something out of science fiction, but they're very much a reality. Essentially, they bring together various data modalities, such as images, text, and audio, and fuse them into a...

We're continuing our discussion on generative adversarial networks, or "GANs" for short. GANs are like a magical dance between two networks – a generator and a discriminator – creating images from random noise. Johannes explains that while GANs may seem like magic, they're a powerful tool for generating realistic images from scratch. We discuss how GANs can be used for generating...

Generative AI is all about creating something new from existing data, and today, we're focusing on one exciting aspect: image-to-image translation. It's not about generating text but transforming images into something entirely different. Think about those fun Snapchat filters that turn your face into a goofy dog – that's image-to-image translation in action. But it goes beyond that. We...

What exactly is geospatial analysis, you ask? Well, in the realm of computer vision, it's all about examining images from a unique perspective – not just your typical cat and dog snapshots, but images taken by satellites from above the Earth's surface. From fine-tuning weather forecasts by identifying cloud patterns and air pressure to predicting forest fires and efficiently delivering aid...

In season two, we are back to explore practical applications of computer vision and their unique challenges. From identifying humans through facial analysis software to assisting doctors in diagnosing patients from medical images, computer vision is making a big impact across various domains. Join us as we unravel the mysteries of object detection, classification, and segmentation, and discover ho...

In the fifth episode we talk about Vision Transformer architectures. An approach for language translation and only recently applied to computer vision. This approach is more suitable for specific tasks as it takes context into account. Terms mentioned: Vision Transformer: https://theaisummer.com/vision-transformer/ Attention and Self Attention: https://vaclavkosar.com/ml/transformers-self-attentio...

In the fourth episode we talk about the prevalent Deep Learning Architectures and their Building blocks. We cover how they work mathematically and how they are stacked together to achieve specific tasks. Terms mentioned: Matrix Multiplication: https://en.wikipedia.org/wiki/Matrix_multiplication_algorithm Activation Function: https://en.wikipedia.org/wiki/Activation_function ⁠Our sponsor is askui:...

In the third episode we dive deeper into Deep Learning and how Convolutional Neural Networks tackle Computer Vision tasks. Terms mentioned: Deep Learning: ⁠https://en.wikipedia.org/wiki/Deep_learning⁠ Convolutional Neural Networks: https://en.wikipedia.org/wiki/Convolutional_neural_network ⁠Our sponsor is askui: Automate UI workflows on every platform!

In the second episode we talk about the origin of Computer vision. Dating back to to a summer school in 1966. We also talk about classical approaches that are still used today as they excel at certain tasks like eye tracking. Terms mentioned: Computer Vision: ⁠https://en.wikipedia.org/wiki/Computer_vision⁠ Kernel Methods: ⁠https://en.wikipedia.org/wiki/Kernel_method⁠ Feature Maps: ⁠https://machine...

In the first episode, we discuss the difference between artificial intelligence, machine learning, and deep learning, and explore the concept of artificial general intelligence. Tune in to learn more about the fascinating world of AI and machine learning! Referenced material: Video: A.I. and Stochastic Parrots | FACTUALLY with Emily Bender and Timnit Gebru Paper 'Stochastic Parrots' ELIZA...