Compound AI Systems, Engineered for the Real World
Compound AI Systems that perceive, reason, and act in the world
From research engineering at IBM Research, MIT and the University of Michigan to designing AI architectures for Fortune 500 enterprises.
Neuro-Symbolic Visual Question Answering on a Robot
Neuro-Symbolic Visual Question Answering on a Robot
While I still have to wait with writing about my core work on Machine Common Sense, here is a small visual question answering (VQA) demo I did on the side. Let me first show you the core VQA functionality: And now let me show that we can additionally point at objects: This demo follows “Neural-Symbolic […]
Side Track: AI Painter – Painting as a Metaphor to Interact with AI Systems
Side Track: AI Painter – Painting as a Metaphor to Interact with AI Systems
Here is a quick personal side experiment I have implemented a while ago to play with an idea I had to leverage a painting application for interacting with an AI system. It was also a good excuse to play with PySide6 a little. Please note that the AI itself here is not impressive at all […]
Sapphire – Dialog System Combining DL, DRL, NLP, Signal Processing and More
Sapphire – Dialog System Combining DL, DRL, NLP, Signal Processing and More
I was the lead developer of Sapphire to which I was invited by IBM’s Speech-CTO and Fellow David Nahamoo. Here is a screenshot of the main system: We built a dialog system for advising and the underlying data collection pipeline. Since this was done on actual advising session great care had to be taken […]
Rearview Mirror: PalmQA, a Question-Answering Ensemble for e-Learning and Research
Rearview Mirror: PalmQA, a Question-Answering Ensemble for e-Learning and Research
My first bigger AI system developed under the supervision of Mohamed Amine Chatti & Ulrik Schroeder. “The scientific mind does not so much provide the right answersas ask the right questions.” Claude Lévi-Strauss 1 Introduction From Emanuel Goldberg’s Statistical Machine and Vannevar Bush’s Memex over collaboration systems like Ted Nelson’s Project Xanadu, Douglas Engelbart’s oN-Line […]
Falk Pollok, MIT-IBM Watson AI Lab Cambridge, USA Abstract Reinforcement Learning (RL) has seen renewed interest sparked by the successful combination of RL with neural models as well as Monte-Carlo Tree Search (MCTS). At first, this development was largely restricted to playing traditional games and video games, but successively one can observe more widespread usage in industry as well from robotics […]
aiengineer.comis the personal technical publication of Falk Pollok (Founder, Augmented Science and Senior Advisory Solution Architect). Strategic acquisition inquiries for theaiengineer.comdomain asset may be directed to me via LinkedIn or the contact page (six-figure reserve / serious institutional buyers only).
Learn More About Me
Get to know more about my work, private interests and journey.
