overfitted
Joined 7 years ago
Karma
18
Submissions
19
Member since
Nov 4
Recent submissions
Comment · 5 years ago
I've been listening in and also followed the Slack channel. It's organised by (both?) featurestore.org and Hopsworks. Anyways, the format of answering questions in the Slack (this time it's featurestore.org's) after the talks was appreciated.
Hope to get the recordings afterwards..
Comment · 6 years ago
While writing this question a thought popped into my mind: Maybe it's actually better like this. Now I/we have to think the idea through before "wasting" someone else's time.
I guess I'm looking for: 1. Have you actually changed anything in your team/organization with regards to innovation? 2. If you were a (mostly or only) remote working company. How have you approached innovation?
Comment · 6 years ago
I think the ability to, as someone mentioned it, have yourself look a bit tidier than you actually are (working from home) could be a huge benifit.
I mean taking away focus on things that doesn't matter in a virtual meeting such as: Where you are sitting - via Virtual Background Your daily hair style status or if you have a nose pimple - Via NVIDIAs AI showcased here. Would be great.
Though replacing yourself with a "digital" avatar I think takes away many of the benefits an actual live meeting provides.
Comment · 6 years ago
If one found this article interesting and are interested in getting some hands-on learning/training on the topic I'd recommend this free open online course provided by a collaboration of Nordic Universities:
https://www.elementsofai.com/
Some might be to easy for you.. then just skim through it, but if Deep Learning is new to you there's some more in-depth interactive exercises in it.
Comment · 6 years ago
I might be falling for something related to Cunningham's Law here but.. I believe the whole article is an effort of trying to answer this question.
Quoting some from the article: "Data warehouses are used primarily by business analysts for interactive querying and for generating historical reports/dashboards on the business. Feature stores are used by both data scientists and by the online/batch applications, and they are fed data by feature pipelines, typically written in Python or Scala/Java. Also, Data warehouses mostly stores data in relational tables, whereas a Feature Store stores it as numerical and categorical features and outputs tensors and/or vectors for training or serving.
Comment · 6 years ago
Great read! I can imagine that a Feature Store could have an impact regarding the challenge of provenance in ML as well. I couldn't find anything on that.
Appreciate the comparison table: Data Warehouse vs Feature Store. Might stea.. re-use that.
Comment · 6 years ago
It's not really clear to me how this really compares to ML Flow.
Comment · 6 years ago
Thanks!
Also the first 10-15 minutes in this recording explains the Feature Store concept and how it can integrate with other ML tools (in this case Sagemaker) incl. slides, examples and demo if you are more of a watch & listen type. https://www.youtube.com/watch?v=3DaTA7o0FHY&list=PLgN6fhzkSu...
Comment · 6 years ago
Yeah well. The "gig economy" proved to be an easy sell when everything was on the rise and booming. Not so nice for the individual 'giggers' when shit hits the fan.
Not the ultra privileged taking the hit though. As usual.
.. though I think the freelancers should've known and taking into account the risk of it though.
Comment · 6 years ago
Many of these problems with models arise because more businesses are buying machine-learning systems but lack the in-house know-how needed to maintain them. Retraining a model can require expert human intervention.
I think this quote is very interesting since it is a practical use case where humans trusting computers and algorithms without enough understanding could be dangerous. One can think, me especially when working with banks, insurance companies and health care industry, that they are slow and too rigourous. Though, in times like these I kind of appreciate the thoroughness in their procurement and policies.
Comment · 6 years ago
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages input perturbations commonly used in computer vision tasks to regularize the value function. Existing model-free approaches, such as Soft Actor-Critic (SAC), are not able to train deep networks effectively from image pixels. However, the addition of our augmentation method dramatically improves SAC's performance, enabling it to reach state-of-the-art performance on the DeepMind control suite, surpassing model-based (Dreamer, SLAC, PlaNet) methods and recently proposed contrastive learning (CURL). Our approach can be combined with any model-free reinforcement learning algorithm, requiring only minor modifications.
- Ilya Kostrikov, Denis Yarats, Rob Fergus
Comment · 6 years ago
Thanks for sharing!
Feels like you've thought about this.
I've been trying to lesser the amount time spent on reading and listening to news. I always feel that I haven't actually missed out on much (anything) when getting home from a one or two week vacation not consuming news daily or multiple times a day.
Have you or anyone else here found a good way to "batch process" news? Say weekly.
RSS feeds I'd use more for interests. Or at least that's how I've thought about it.
Comment · 6 years ago
What is the stock value latency within EU and US?