Essays about: "Black box"
Showing result 31 - 35 of 259 essays containing the words Black box.
-
31. Explainable AI by Training Introspection
University essay from Högskolan i Halmstad/Akademin för informationsteknologiAbstract : Deep Neural Networks (DNNs) are known as black box algorithmsthat lack transparency and interpretability for humans. eXplainableArtificial Intelligence (XAI) is introduced to tackle this problem. MostXAI methods are utilized post-training, providing explanations of themodel to clarify its predictions and inner workings for human understanding. READ MORE
-
32. Looking into the black box: The roles of development workers in enhancing climate resilience and gender equality for ethnic minority women through the EmPower project in Vietnam
University essay from Göteborgs universitet/Institutionen för globala studierAbstract : The climate change-gender nexus has increasingly become the arena in which adaptation interventions take place. One such intervention is the EmPower program in the Asia-Pacific region by UN Women and UNEP. This research is a case study on how one program component on women’s renewable energy entrepreneurship is implemented in Vietnam. READ MORE
-
33. Assessing the Value of Development Assistance According to the Recipients: A Case Study of Georgian Organisations’ Perspectives on Estonian Development Assistance
University essay from Lunds universitet/Graduate SchoolAbstract : Factors contributing to valuable development assistance are often perceived as a "black box," due to heterogeneity of development aid motives. This research brings out that too often, the value of aid is assessed from the perspectives of the donors rather than from its recipients. READ MORE
-
34. Expressibility of multiscale physics in deep networks
University essay from Umeå universitet/Institutionen för fysikAbstract : Motivated by the successes in the field of deep learning, the scientific community has been increasingly interested in neural networks that are able to reason about physics. As neural networks are universal approximators, they could in theory learn representations that are more efficient than traditional methods whenever improvements are theoretically possible. READ MORE
-
35. The Implementation and Evaluation of Learning Approaches to State Filtering
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : State estimation uses measurements of a system’s output to estimate the state. A particular method within state estimation is filtering, which estimates the state using measurements up to and including the current time. READ MORE
