Artificial Intelligence

The Power of Graph Neural Networks: Understanding the Future of AI - Part 2/2 (Ep.224)

In this episode of our podcast, we dive deep into the fascinating world of Graph Neural Networks.
First, we explore Hierarchical Networks, which allow for the efficient representation and analysis of complex graph structures by breaking them down into smaller, more manageable components.
Next, we turn our attention to Generative Graph Models, which enable the creation of new graph structures that are similar to those in a given dataset. We discuss the inner workings of these models and their potential applications in fields such as drug discovery and social network analysis.
Finally, we delve into the essential Pooling Mechanism, which allows for the efficient passing of information across different parts of the graph neural network. We examine the various types of pooling mechanisms and their advantages and disadvantages.
Whether you're a seasoned graph neural network expert or just starting to explore the field, this episode has something for you. So join us for a deep dive into the power and potential of Graph Neural Networks.
 
References
Machine Learning with Graphs - http://web.stanford.edu/class/cs224w/
A Comprehensive Survey on Graph Neural Networks - https://arxiv.org/abs/1901.00596

The Power of Graph Neural Networks: Understanding the Future of AI - Part 1/2 (Ep.223)

In this episode, I explore the cutting-edge technology of graph neural networks (GNNs) and how they are revolutionizing the field of artificial intelligence. I break down the complex concepts behind GNNs and explain how they work by modeling the relationships between data points in a graph structure.
I also delve into the various real-world applications of GNNs, from drug discovery to recommendation systems, and how they are outperforming traditional machine learning models.
Join me and demystify this exciting area of AI research and discover the power of graph neural networks.

Leveling Up AI: Reinforcement Learning with Human Feedback (Ep. 222)

In this episode, we dive into the not-so-secret sauce of ChatGPT, and what makes it a different model than its predecessors in the field of NLP and Large Language Models.
We explore how human feedback can be used to speed up the learning process in reinforcement learning, making it more efficient and effective.
Whether you're a machine learning practitioner, researcher, or simply curious about how machines learn, this episode will give you a fascinating glimpse into the world of reinforcement learning with human feedback.
 
Sponsors
This episode is supported by How to Fix the Internet, a cool podcast from the Electronic Frontier Foundation and Bloomberg, global provider of financial news and information, including real-time and historical price data, financial data, trading news, and analyst coverage.
 
References
Learning through human feedback
https://www.deepmind.com/blog/learning-through-human-feedback
 
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
https://arxiv.org/abs/2204.05862

The promise and pitfalls of GPT-4 (Ep. 221)

In this episode, we explore the potential of the highly anticipated GPT-4 language model and the challenges that come with its development. From its ability to generate highly coherent and creative text to concerns about ethical considerations and the potential misuse of such technology, we delve into the promise and pitfalls of GPT-4. Join us as we speak with experts in the field to gain insights into the latest developments and the impact that GPT-4 could have on the future of natural language processing.
 
 

AI’s Impact on Software Engineering: Killing Old Principles? (Ep. 220)

In this episode, we dive into the ways in which AI and machine learning are disrupting traditional software engineering principles. With the advent of automation and intelligent systems, developers are increasingly relying on algorithms to create efficient and effective code. However, this reliance on AI can come at a cost to the tried-and-true methods of software engineering. Join us as we explore the pros and cons of this paradigm shift and discuss what it means for the future of software development.

Edge AI applications for military and space [RB] (Ep. 219)

[RB] Online learning is better than batch, right? Wrong! (Ep. 216)

In this episode I speak about online learning systems and why blindly choosing such a paradigm can lead to very unpredictable and expensive outcomes.Also in this episode, I have to deal with an intruder :)
 
 
Links
Birman, K.; Joseph, T. (1987). "Exploiting virtual synchrony in distributed systems". Proceedings of the Eleventh ACM Symposium on Operating Systems Principles - SOSP '87. pp. 123–138. doi:10.1145/41457.37515. ISBN 089791242X. S2CID 7739589.
 

Chatting with ChatGPT: Pros and Cons of Advanced Language AI (Ep. 215)

In this episode, I'll be discussing the capabilities and limitations of ChatGPT, an advanced language AI model. I'll go over its power to understand and respond to natural language, and its applications in tasks such as language translation and text summarization. However, I'll also touch on the challenges that still need to be overcome such as bias and data privacy concerns. Tune in for a comprehensive look at the current state of advanced language AI.
 
References
https://datascienceathome.com/have-you-met-shannon-conversation-with-jimmy-soni-and-rob-goodman-about-one-of-the-greatest-minds-in-history/
 

Accelerating Perception Development with Synthetic Data (Ep. 214)

In this episode I am with Kevin McNamara, founder and CEO of Parallel Domain. We speak about a very effective method to generate synthetic data that is currently in production at Parallel Domain.
Enjoy the show!
 
 
References
Parallel Domain Synthetic Data Improves Cyclist Detection (blog post):
https://paralleldomain.com/parallel-domain-synthetic-data-improves-cyclist-detection/ 
 
Beating the State of the Art in Object Tracking with Synthetic Data:
https://paralleldomain.com/beating-the-state-of-the-art-in-object-tracking-with-synthetic-data/ 
 
Parallel Domain Open Synthetic Dataset:
https://paralleldomain.com/open-datasets/bicycle-detection 
 
How Toyota Research Institute Trains Better Computer Vision Models with PD Synthetic Data (interview):
https://www.youtube.com/watch?v=QIYttoVxf2w
 
Career Opportunities:
https://paralleldomain.com/careers

Edge AI applications for military and space [RB] (Ep. 213)

Our Sponsors
NordPass Business has developed a password manager, that will save you a lot of time and energy whenever you need access to business accounts, work across devices, even with the other members of your team, or whenever you need to share sensitive data with your colleagues, or make payments efficiently. All this with the highest standard of cyber secure technology.
See NordPass Business in action now with a 3-month free trial herehttps://nordpass.com/DATASCIENCE with code DATASCIENCE
 
 
Amethix works to create and maximize the impact of the world’s leading corporations and startups, so they can create a better future for everyone they serve. We provide solutions in AI/ML, Fintech, Healthcare/RWE, and Predictive maintenance.