Lecture 9: Hardware and Software

Lecture 9 gives an overview of the hardware and software systems used in deep learning. We contrast CPUs with graphics processing units (GPUs), and see how the massively parallel architecture of GPUs allows them to accelerate deep learning workloads, and how the rapidly improving hardware performance has been a driving force in deep learning. We also discuss the special-purpose hardware (tensor cores, tensor processing units) that have recently been introduced to further accelerate deep learning. On the software side, we focus on the two most widely used deep learning frameworks: PyTorch and TensorFlow. We see how these two frameworks realize the notion of a computational graph in software, and contrast dynamic vs static computational graphs.

_________________________________________________________________________________________________

Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks.

[jackroubaud]

This is really really excellent series of video. It takes time, but it's definitely worth it. it gathers all pieces learnt along the way add new ones, and put all of them into order.
Many thanks for sharing this ! great contribution to computer vision with AI

[KovarishxD]

I wish more universities would publish their courses and lectures. This is super good for those who doesn't have the privilege to attend such great courses.

[cc-oeol]

This is really good lecture that teaches us the concepts of PyTorch and how to use it in great details.
Afaik, many lectures only focus on theory or something, and they seldom teach you how to TRANSLATE math INTO code.
I do consider that as very irresponsible, it's like your calculus prof only teaches you what is limit and what is Riemann integral, but never show you how to integrate ln(x).

[rajivb]

In the HW part, can you throw some light on Embedded platforms, boards or Modules which can support Deep Learning like Google Coral Dev Board, NVIDIA Jetson Nano, BeagleBone AI Boards which are specific to embedded machine learning for computer vision ?

[alexrider]

If I watched this lecture in 2019, I would've bought NVIDIA stock in 2020, and in 2024, I'd be rich

[sardorabdirayimov]

Watching about pytorch and tesorflow after 4 years is quite funny