Refine
Document Type
- Article (1)
- Bachelor Thesis (1)
- Master's Thesis (1)
Language
- English (3)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Keywords
- AI (3) (remove)
Institute
In the last years generative models have gained large public attention due to their high level of quality in generated images. In short, generative models learn a distribution from a finite number of samples and are able then to generate infinite other samples. This can be applied to image data. In the past generative models have not been able to generate realistic images, but nowadays the results are almost indistinguishable from real images.
This work provides a comparative study of three generative models: Variational Autoencoder (VAE), Generative Adversarial Network (GAN) and Diffusion Models (DM). The goal is not to provide a definitive ranking indicating which one of them is the best, but to qualitatively and where possible quantitively decide which model is good with respect to a given criterion. Such criteria include realism, generalization and diversity, sampling, training difficulty, parameter efficiency, interpolating and inpainting capabilities, semantic editing as well as implementation difficulty. After a brief introduction of how each model works on the inside, they are compared against each other. The provided images help to see the differences among the models with respect to each criterion.
To give a short outlook on the results of the comparison of the three models, DMs generate most realistic images. They seem to generalize best and have a high variation among the generated images. However, they are based on an iterative process, which makes them the slowest of the three models in terms of sample generation time. On the other hand, GANs and VAEs generate their samples using one single forward-pass. The images generated by GANs are comparable to the DM and the images from VAEs are blurry, which makes them less desirable in comparison to GANs or DMs. However, both the VAE and the GAN, stand out from the DMs with respect to the interpolations and semantic editing, as they have a latent space, which makes space-walks possible and the changes are not as chaotic as in the case of DMs. Furthermore, concept-vectors can be found, which transform a given image along a given feature while leaving other features and structures mostly unchanged, which is difficult to archive with DMs.
Context: Higher education is changing at an accelerating pace due to the widespread use of digital teaching and emerging technologies. In particular, AI assistants such as ChatGPT pose significant challenges for higher education institutions because they bring change to several areas, such as learning assessments or learning experiences.
Objective: Our objective is to discuss the impact of AI assistants in the context of higher education, outline possible changes to the context, and present recommendations for adapting to change.
Method: We review related work and develop a conceptual structure that visualizes the role of AI assistants in higher education.
Results: The conceptual structure distinguishes between humans, learning, organization, and disruptor, which guides our discussion regarding the implications of AI assistant usage in higher education. The discussion is based on evidence from related literature.
Conclusion: AI assistants will change the context of higher education in a disruptive manner, and the tipping point for this transformation has already been reached. It is in our hands to shape this transformation.
AlphaGo’s victory against Lee Sedol in the game of Go has been a milestone in artificial intelligence. After this success, the team behind the program further refined the architecture and applied it to many other games such as chess or shogi. In the following thesis, we try to apply the theory behind AlphaGo and its successor AlphaZero to the game of Abalone. Due to limitations in computational resources, we could not replicate the same exceptional performance.