Eric Larson

@ec_larson

Associate Professor in Computer Science at Southern Methodist University, Dallas

Vrijeme pridruživanja: veljača 2011.

Tweetovi

Blokirali ste korisnika/cu @ec_larson

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ec_larson

  1. proslijedio/la je Tweet
    30. sij

    I was just thinking it would be cool if you could do hyperparameter tuning directly in Keras and then found this blog post published yesterday 🤯 The best part? I got it working in 5 minutes!

    Poništi
  2. proslijedio/la je Tweet
    29. sij

    ML Fairness Gym is a set of components for building simple simulations that explore the potential long-run impacts of deploying machine learning-based decision systems in social environments, based on OpenAI Gym interface.

    Poništi
  3. proslijedio/la je Tweet
    25. sij

    Generative Adversarial Networks are a pretty active appl. and research field, and I am really glad that there are the occasional reviews that summarize recent developments: "A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications"

    Poništi
  4. proslijedio/la je Tweet
    23. sij

    Q-learning is difficult to apply when the number of available actions is large. We show that a simple extension based on amortized stochastic search allows Q-learning to scale to high-dimensional discrete, continuous or hybrid action spaces:

    Poništi
  5. proslijedio/la je Tweet
    14. sij

    The best SSL approaches to learning visual features today use Siamese networks to learn embeddings. Examples: two recent papers from FAIR, "Pretext-Invariant Representation Learning" (Misra et al.) and "MoCo" (He et al.).

    Poništi
  6. proslijedio/la je Tweet
    13. sij

    I published a new article on the blog: Active Transfer Learning with PyTorch. Read about adapting Machine learning models with the knowledge that some data points will later get correct human labels, even if the model doesn't yet know the labels:

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    9. sij

    I feel strange writing this at this time but I should tweet about papers at some point. This one is with the amazing @jo_historian--my first paper with a historian! I learned so much from her. People always talk about using ML for X, digital humanities etc

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    23. pro 2019.

    Since the start of TAMEST's protégé program, several have gone on to become O’Donnell Awards recipients or achieve election to . This year, we welcome 42 talented, early career researchers to . Meet the TAMEST 2020 Class of Protégés:

    Poništi
  9. proslijedio/la je Tweet
    16. pro 2019.

    We published HydroSense at UbiComp'09, which introduced a new method to automatically detect & classify water usage from a single sensing point using machine learning + water pressure signatures. Amazing to see that it is now on shelves at Best Buy: 1/n

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    1. pro 2019.

    Good read on the overselling of AI results. An Epidemic of AI Misinformation

    Poništi
  11. proslijedio/la je Tweet
    30. stu 2019.

    "Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks" -"[a] combination of a normalization and an activation function, that can be used as a drop-in replacement for other normalizations and activations"

    Poništi
  12. proslijedio/la je Tweet

    Check out our new project on Teaching Computer Science and Computational Thinking with Community Gaming Funded by (Project 1933848) with in collaboration with

    Poništi
  13. proslijedio/la je Tweet
    11. stu 2019.

    Do you like Minecraft? RME is 2 students to support a NEW GRANT integrating + Computing based curriculum directly into Minecraft. More info - contact lkgeller@smu.edu or kmilligan@smu.edu

    Photo by Nina PhotoLab
    Poništi
  14. proslijedio/la je Tweet
    11. stu 2019.

    And here's another grant-funded opportunity for doctoral training in STEM Education:

    Poništi
  15. proslijedio/la je Tweet
    5. stu 2019.

    Understanding UMAP - an interactive introduction to the algorithm and how to us (and mis-use) it from and . A must read for anyone interested in dimension reduction.

    Poništi
  16. proslijedio/la je Tweet
    17. lis 2019.

    Apple Research is looking for research interns for 2020 in Pittsburgh & Seattle! We do research at the intersection of HCI+ML, with a specific focus on Accessibility, Design+ML, InfoViz, and Sensing. Read if you're interested in learning more!

    Poništi
  17. proslijedio/la je Tweet
    17. lis 2019.
    Poništi
  18. 22. lis 2019.

    So excited to be a CoPI in this research! Hope we can have a positive impact CS instruction.

    Poništi
  19. proslijedio/la je Tweet
    25. ruj 2019.

    Xavier initialization or Standard Normal? Visualize how different initialization methods affect layer activations in our AI Notes tutorial:

    Poništi
  20. proslijedio/la je Tweet
    19. ruj 2019.

    There is a lot of exciting work happening at the intersection of STEM and computer science education @ the NSF STEM+C PI Meeting in Alexandria

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·