Search

Search Funnelback University

Search powered by Funnelback
10 results 20 results 50 results
Relevance Date (Newest first) Date (Oldest first) Title (A-Z) Title (Z-A) Distance URL (A-Z) URL (Z-A) Shuffle
Did you mean economiespast |u:mlg.eng.cam.ac.uk?
21 - 30 of 47 search results for Economics test |u:mlg.eng.cam.ac.uk where 12 match all words and 35 match some words.

  1. Results that match 1 of 2 words

  2. Natural-Gradient Variational Inference 2: ImageNet-scale · Cambridge…

    https://mlg.eng.cam.ac.uk/blog/2021/11/24/ngvi-bnns-part-2.html
    12 Apr 2024: Reducing the prior precision $delta$ results in higher validation accuracy, but also a larger train-test gap, corresponding to more overfitting. ... Continual Learning: I personally think continual learning is a very good way to test approximate Bayesian

  3. ML-IRL: Machine Learning in Real Life Workshop at ICLR ...

    https://mlg.eng.cam.ac.uk/adrian/ML_IRL_2020-CLUE.pdf
    19 Jun 2024: We evaluate the test set of fours, sevens, and nines with our BNN. ... This group was able to reach an accuracyof 88% on unseen test points.

  4. Exploring Properties of the Deep Image Prior Andreas…

    https://mlg.eng.cam.ac.uk/adrian/NeurIPS_2019_DIP7.pdf
    19 Jun 2024: To test the nature of these outputs we introduce a novel saliencymap approach, termed MIG-SG. ... To test this, we evaluated the sensitivity of DIP to changes innetwork architecture.

  5. Ten papers from the group to appear at ICML 2016 | Cambridge Machine…

    https://mlg.eng.cam.ac.uk/news/ten-papers-from-the-group-to-appear-at-icml-2016/
    10 Apr 2024: Train and Test Tightness of LP Relaxations in Structured Prediction. Ofer Meshi, Mehrdad Mahdavi, Adrian Weller and David Sontag.

  6. ML-IRL: Machine Learning in Real Life Workshop at ICLR ...

    https://mlg.eng.cam.ac.uk/adrian/ML_IRL_2020-Counterfactual_Accuracy.pdf
    19 Jun 2024: would we have to give up so that the predictionfor the test point would change? ... 2017)), and then we constrain fora random test point to obtain counterfactual accuracy.

  7. Orthogonal estimation of Wasserstein distances Mark Rowland*, Jiri…

    https://mlg.eng.cam.ac.uk/adrian/slicedwasserstein_poster.pdf
    19 Jun 2024: Naturally incorporate spatial information. • Applications from economics to machine learning.

  8. Evaluating and Aggregating Feature-based Model Explanations

    https://mlg.eng.cam.ac.uk/adrian/IJCAI20_EvaluatingAndAggregating.pdf
    19 Jun 2024: For Iris [Dua and Graff, 2017], we train our modelto 96% test accuracy. ... 45). Table 2: Faithfulness µF averaged over a test set: (Zero Baseline,Training Average Baseline).

  9. The Geometry of Random Features Krzysztof Choromanski∗1 Mark…

    https://mlg.eng.cam.ac.uk/adrian/geometry.pdf
    19 Jun 2024: pre-dictive distribution obtained by an exactly-trained GP, and(ii) predictive RMSE on test sets. ... Figure 8: Approximate GP regression results on Bostondataset. Reported numbers are average test RMSE, alongwith bootstrap estimates of standard error

  10. Seven new papers from the group to appear at NIPS 2015 in Montreal |…

    https://mlg.eng.cam.ac.uk/news/seven-new-papers-from-the-group-to-appear-at-nips-2015-in-montreal/
    10 Apr 2024: The list of papers are:. Statistical Model Criticism using Kernel Two Sample Tests.

  11. Leader Stochastic Gradient Descent for DistributedTraining of Deep…

    https://mlg.eng.cam.ac.uk/adrian/NeurIPS2019_LSGD_preprint.pdf
    19 Jun 2024: Test error for the center variableversus wall-clock time (original plot on the left and zoomed onthe right). ... Test loss is reported in Figure 13 in the Supplement. Finally, in Figure 6 we report theempirical results for ResNet50run on ImageNet.

Refine your results

clear all

Date

Search history

Recently clicked results

Recently clicked results

Your click history is empty.

Recent searches

Recent searches

Your search history is empty.