- 27
- 24 124
ArnoSolin
Приєднався 1 січ 2012
Introduction to AI (2024): What is Artificial Intelligence?
The first lecture on the Aalto University course 'CS-C1000 - Introduction to Artificial Intelligence'. Lectured by Assistant Professor Arno Solin at Aalto University in the spring term of 2024.
Chapters:
0:00:00 - Introduction to the Course
0:01:57 - Exploring the Definition of AI
0:03:02 - Addressing Common AI Misconceptions
0:04:11 - A Journey Through AI's History
0:11:13 - Understanding the Turing Test
0:13:02 - Advancements in AI Tools and Technologies
0:17:33 - Differentiating Strong AI vs. Weak AI and General AI vs. Narrow AI
0:36:03 - Discussing the Current Hype Around AI
0:49:06 - Real-World AI Examples in Everyday Technology
0:58:01 - The Role of AI in Generating Art and Images
1:08:06 - Summary and What to Expect Next
Chapters:
0:00:00 - Introduction to the Course
0:01:57 - Exploring the Definition of AI
0:03:02 - Addressing Common AI Misconceptions
0:04:11 - A Journey Through AI's History
0:11:13 - Understanding the Turing Test
0:13:02 - Advancements in AI Tools and Technologies
0:17:33 - Differentiating Strong AI vs. Weak AI and General AI vs. Narrow AI
0:36:03 - Discussing the Current Hype Around AI
0:49:06 - Real-World AI Examples in Everyday Technology
0:58:01 - The Role of AI in Generating Art and Images
1:08:06 - Summary and What to Expect Next
Переглядів: 564
Відео
Introduction to AI (2024): Search, Logic, and Symbolic AI
Переглядів 348День тому
The fifth lecture on the Aalto University course 'CS-C1000 - Introduction to Artificial Intelligence'. Lectured by Assistant Professor Arno Solin at Aalto University in the spring term of 2024.
Introduction to AI (2024): Impact and Ethics of AI
Переглядів 217День тому
The sixth lecture on the Aalto University course 'CS-C1000 - Introduction to Artificial Intelligence'. Lectured by Assistant Professor Arno Solin at Aalto University in the spring term of 2024.
Introduction to AI (2024): Deep Learning
Переглядів 539День тому
The third lecture on the Aalto University course 'CS-C1000 - Introduction to Artificial Intelligence'. Lectured by Assistant Professor Arno Solin at Aalto University in the spring term of 2024.
Introduction to AI (2024): Reinforcement Learning
Переглядів 385День тому
The fourth lecture on the Aalto University course 'CS-C1000 - Introduction to Artificial Intelligence'. Lectured by Assistant Professor Arno Solin at Aalto University in the spring term of 2024.
Introduction to AI (2024): Machine Learning
Переглядів 557День тому
The second lecture on the Aalto University course 'CS-C1000 - Introduction to Artificial Intelligence'. Lectured by Assistant Professor Arno Solin at Aalto University in the spring term of 2024.
Fixing overconfidence in dynamic neural networks (WACV 2024)
Переглядів 1306 місяців тому
In this WACV 2024 conference presentation, we explore a novel approach to enhancing dynamic neural networks through post-hoc uncertainty quantification. Dynamic neural networks adapt their computational cost based on input complexity, offering a solution to the growing size of deep learning models. However, differentiating between complex and simple inputs remains a challenge due to unreliable ...
Generative Modelling with Inverse Heat Dissipation (ICLR 2023)
Переглядів 332Рік тому
While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and the empirical success of coarse-to-fine modelling, we propose a new diffusion-like model that generates images through stochastically reversing the heat equa...
Periodic activation functions induce stationarity (NeurIPS 2021)
Переглядів 1782 роки тому
Video presentation by Lassi Meronen for the paper: Lassi Meronen, Martin Trapp, and Arno Solin (2021). Periodic activation functions induce stationarity. In Advances in Neural Information Processing Systems 34 (NeurIPS). 📄 arXiv: arxiv.org/abs/2110.13572 💻 code: github.com/AaltoML/PeriodicBNN
Scalable inference in SDEs by direct matching of the Fokker-Planck-Kolmogorov equation (NeurIPS)
Переглядів 1672 роки тому
Video presentation by Arno Solin, Ella Tamir, and Prakhar Verma for the paper: Arno Solin, Ella Tamir, and Prakhar Verma (2021). Scalable inference in SDEs by direct matching of the Fokker-Planck-Kolmogorov equation. In Advances in Neural Information Processing Systems 34 (NeurIPS). 📄 arXiv: arxiv.org/abs/2110.15739 💻 code: github.com/AaltoML/scalable-inference-in-SDEs
Dual parameterization of sparse variational Gaussian processes
Переглядів 1232 роки тому
Video presentation by Vincent Adam for the paper: Vincent Adam, Paul E. Chang, Mohammad Emtiyaz Khan, and Arno Solin (2021). Dual parameterization of sparse variational Gaussian processes. In Advances in Neural Information Processing Systems 34 (NeurIPS). 📄 arXiv: arxiv.org/abs/2111.03412 💻 code: github.com/AaltoML/t-SVGP
Spatio-temporal variational Gaussian processes (NeurIPS 2021)
Переглядів 8552 роки тому
Video presentation by Oliver Hamelijnck for the paper: Oliver Hamelijnck, William J. Wilkinson, Niki Andreas Loppi, Arno Solin, and Theo Damoulas (2021). Spatio-temporal variational Gaussian processes. In Advances in Neural Information Processing Systems 34 (NeurIPS). 📄 arXiv: arxiv.org/abs/2111.01732 💻 code: github.com/AaltoML/spatio-temporal-GPs
Machine Learning with Signal Processing (ICML 2020 Tutorial)
Переглядів 3,8 тис.3 роки тому
This is a compilation video of the four parts (á 30 min) of the "Machine Learning with Signal Processing" tutorial given at the International Conference on Machine Learning (ICML) in July 2020. The video only contains the presentation material itself; for Q&A, please see the separate videos hosted on SlidesLive by the conference organizers. Abstract: Many ML tasks share practical goals and theo...
Stationary Activations for Uncertainty Calibration in Deep Learning
Переглядів 1903 роки тому
Presentation video for the paper: Lassi Meronen, Christabella Irwanto, and Arno Solin (2020). Stationary Activations for Uncertainty Calibration in Deep Learning. Advances in Neural Information Processing Systems (NeurIPS). arXiv preprint: arxiv.org/abs/2010.09494
Fast variational learning in state-space Gaussian process models
Переглядів 4803 роки тому
Video presentation for the paper: Paul E. Chang, William J. Wilkinson, Mohammad Emtiyaz Khan, and Arno Solin (2020). Fast variational learning in state-space Gaussian process models. In IEEE International Workshop on Machine Learning for Signal Processing (MLSP). Pre-print available on arXiv: arxiv.org/abs/2007.05994
Movement Tracking by Optical Flow Assisted Inertial Navigation (talk)
Переглядів 4254 роки тому
Movement Tracking by Optical Flow Assisted Inertial Navigation (talk)
Iterative path reconstruction for large-scale inertial navigation on smartphones @ FUSION 2019
Переглядів 1774 роки тому
Iterative path reconstruction for large-scale inertial navigation on smartphones @ FUSION 2019
Multi-view stereo by temporal nonparametric fusion
Переглядів 1,6 тис.5 років тому
Multi-view stereo by temporal nonparametric fusion
Infinite-Horizon Gaussian Processes (NeurIPS/NIPS 3min video)
Переглядів 1,6 тис.5 років тому
Infinite-Horizon Gaussian Processes (NeurIPS/NIPS 3min video)
ADVIO: An Authentic Dataset for Visual-Inertial Odometry #16
Переглядів 2 тис.5 років тому
ADVIO: An Authentic Dataset for Visual-Inertial Odometry #16
Robust Gyroscope-Aided Camera Self-Calibration
Переглядів 7676 років тому
Robust Gyroscope-Aided Camera Self-Calibration
Scalable Magnetic Field SLAM in 3D Using Gaussian Process Maps
Переглядів 1,7 тис.6 років тому
Scalable Magnetic Field SLAM in 3D Using Gaussian Process Maps
Inertial Odometry on Handheld Smartphones
Переглядів 2 тис.6 років тому
Inertial Odometry on Handheld Smartphones
Terrain navigation in the magnetic landscape: Particle filtering for indoor positioning
Переглядів 9416 років тому
Terrain navigation in the magnetic landscape: Particle filtering for indoor positioning
PIVO: Probabilistic inertial-visual odometry through the city
Переглядів 1,2 тис.6 років тому
PIVO: Probabilistic inertial-visual odometry through the city
PIVO: Probabilistic inertial-visual odometry compared with Tango
Переглядів 3626 років тому
PIVO: Probabilistic inertial-visual odometry compared with Tango
Interpolation of the magnetic field by Gaussian processes
Переглядів 2,5 тис.8 років тому
Interpolation of the magnetic field by Gaussian processes
How does online inference step work then? Say I observe additional accidents in coal or airlines, but there is no time to retrain the GP. Do I simply add observations to GP data and then predict for unseen steps?
Nice Lecture
Thanks Professor Solin for crisp and concise explanations!
very insightful. What if the stroller is not stopped intermittently, but rather only at the starting and destination point...Will the biases be too big to create big positional errors?
Nice video, could you share code? I am interesting in tiny trajectories but I am not sure what error to expect.
You can have swapped around neural nets too. With fixed dot products (enacted with fast transforms) and adjustable activation functions. Parametric (adjustable) ReLU is anyway a known thing. Of course you have to prevent the first transform from taking the spectrum of the input which you can do using a random fixed pattern of sign flips. And use a final transform as a readout layer. The fast Walsh Hadamard transform is good.