Een actieonderzoek naar de ontwikkeling van een leerlingversterkend onderwijsprogramma met het doel leerlingen met een visuele beperking beter voor te bereiden op hun transitie naar volwassenheid en waar mogelijk een betaalde baan. Belangrijke thema's: inclusie en exclusie, empowerment, stem van de leerling, transitie naar volwassenheid en het burgerschapsmodel tegenover het medische model.
This research paper looks at a selection of science-fiction films and its connection with the progression of the use of television, telephone and print media. It also analyzes statistical data obtained from a questionnaire conducted by the research group regarding the use of communication media.
![Does Science-Fiction predict [or change] the future?](https://publinova-harvester-content-prod.s3.amazonaws.com/thumbnails/files/previews/pdf/20240419032400973719.adbf7edd-9619-4d0e-9a17-e0e7096adc7f-thumbnail-400x300.png)
We present a novel architecture for an AI system that allows a priori knowledge to combine with deep learning. In traditional neural networks, all available data is pooled at the input layer. Our alternative neural network is constructed so that partial representations (invariants) are learned in the intermediate layers, which can then be combined with a priori knowledge or with other predictive analyses of the same data. This leads to smaller training datasets due to more efficient learning. In addition, because this architecture allows inclusion of a priori knowledge and interpretable predictive models, the interpretability of the entire system increases while the data can still be used in a black box neural network. Our system makes use of networks of neurons rather than single neurons to enable the representation of approximations (invariants) of the output.
LINK
