jisaacso

Cool!

Agreed that PyTorch tutorials are a great place to start. Specific to flexattention, the blog references the accompanying attention gym, which has a series of examples of how to use flex: https://github.com/pytorch-labs/attention-gym/

I use to fly BOS <> SFO frequently.

One contributing factor is that the jetstream is stronger in winter months than summer months. Flights from BOS to SFO are up to 1 hour longer (heading into the jetstream) and 1 hour shorter from SFO to BOS (strong tailwinds).

In winter months, some airline's direct flights have to occasionally land and refuel mid-country[1]. I've experienced this first hand a couple times.

[1] https://thepointsguy.com/2018/02/winds-forcing-virgin-americ...

Asimov | UX Engineer | Boston, MA | Full-time | ONSITE | www.asimov.io

Hi from Asimov! We’re a small team of HNers fueled by a vision to transition synthetic biology to a fully-fledged engineering discipline. Check out some of our work at www.github.com/CIDARLAB/cello and our mission at www.asimov.io/blog

As our user interface technical lead you will have the opportunity to:

* Build reactive, web-based navigation of our genetically-engineered product offerings including those for genetic design, cellular debugging, and biophysical modeling

* Partner with machine learners to architect interfaces for intuitive interactions between humans and artificial intelligence systems

* Define the standards, processes, and portfolio that will drive UI engineering and design growth over the coming years

* Create aesthetically striking and scientifically-accurate visualizations of engineered genetic and cellular systems for product pages, presentations, and blog posts

Perks

* We believe in creating a lifelong company by avoiding burnout and focusing on long term impact

* Above market compensation including significant equity, full medical/dental/vision, flexible PTO, frequent team lunches, happy hours, offsites (borda borg!), Hackathons, snacks and a fully stocked coffee lab

If you’re interested please send me an email at joe@asimov.io or apply online at www.asimov.io/careers

Yes! As mindcrime says, Cello is a great platform that compiles Verilog to DNA circuits. Check it out https://github.com/CIDARLAB/cello

Asimov | Machine Learning Engineer | Boston, MA | Full-time

Hi from Asimov! We’re a small team of HNers fueled by a vision to transition synthetic biology to a fully-fledged engineering discipline. Check out some of our work at www.github.com/CIDARLAB/cello and our mission at www.asimov.io/blog

ML Engineer Prerequisites:

* 4+ years hands on experience as a ML engineer in industry

* knowledge of modern methods in reinforcement learning, graph neural networks, breadth of knowledge across supervised and unsupervised learning and experience applying these models to solve biophysical or bioinformatics problems

Perks

* We believe in creating a lifelong company by avoiding burnout and focusing on long term impact

* Frequent team lunches, happy hours, offsites (borda borg!), Hackathons, snacks and a fully stocked coffee lab

If you’re interested please send me an email at joe@asimov.io or apply online at www.asimov.io/careers

Asimov | Software Engineer, Machine Learning Engineer | Boston, MA | Full-time

Hi from Asimov! We’re a small team of HNers fresh off of our seed funding lead by Andreessen Horowitz. We’re fueled by a vision to transition synthetic biology to a fully-fledged engineering discipline. Check out some of our work at www.github.com/CIDARLAB/cello and our mission at www.asimov.io/blog

Search Keywords: deep learning, sequence to sequence learning, bioinformatics, cloud infrastructure, python, tensorflow, microservices, biotech, Boston, Cambridge

Prerequisites:

* 4+ years hands on experience as a SWE or ML engineer in industry

* ML engineer: knowledge of modern methods in reinforcement learning, generative adversarial models, breadth of knowledge across supervised and unsupervised learning and experience applying these models in software

* SWE: knowledge of cloud infrastructure, large scale data warehousing, build/test/deploy platform development

Biological data scientist: proficiency in scripting, statistical analysis of genomic data sets, NGS, flow cytometry reads and RNAseq

Excitement to learn a tremendous amount about genetics, bio hacking, genetic circuit design

* Excitement to own your own roadmap and prioritization

Perks

* We believe in creating a lifelong company by avoiding burnout and focusing on long term impact

* Frequent team lunches, happy hours, offsites (borda borg!), snacks and a fully stocked coffee lab

If you’re interested please send me an email at joe@asimov.io or apply online at www.asimov.io/careers

Asimov | Software Engineer, Machine Learning Engineer | Boston, MA | Full-time

Hi from Asimov! We’re a small team of HNers fresh off of our seed funding lead by Andreessen Horowitz. We’re fueled by a vision to transition synthetic biology to a fully-fledged engineering discipline. We’re building our our initial software team and need help with everything at the intersection of infrastructure, software systems, data ingestion and storage and machine learning for predicting optimal genetic circuit design. Check out some of our work at www.github.com/CIDARLAB/cello and our mission at www.asimov.io/blog

Search Keywords: deep learning, sequence to sequence learning, bioinformatics, cloud infrastructure, python, tensorflow, microservices, biotech, Boston, Cambridge

Prerequisites: * 4+ years hands on experience as a SWE or ML engineer in industry * ML engineer: knowledge of modern methods in reinforcement learning, generative adversarial models, breadth of knowledge across supervised and unsupervised learning and experience applying these models in software * SWE: knowledge of cloud infrastructure, large scale data warehousing, build/test/deploy platform development * Excitement to learn a tremendous amount about genetics, bio hacking, genetic circuit design * Excitement to own your own roadmap and prioritization

Perks: * Flexible working hours, develop when you are most productive * We believe in creating a lifelong company by avoiding burnout and focusing on long term impact * Frequent team lunches, happy hours, offsites (borda borg!), snacks and a fully stocked coffee lab * Cross pollination: We’re an awesome team of scientists and engineers from diverse technical backgrounds. Learn cutting edge synthetic biology from world experts!

If you’re interested please send me an email at joe@asimov.io or apply online at www.asimov.io/careers

Asimov | Software Engineer, Machine Learning Engineer | Boston, MA | Full-time

Hi from Asimov! We’re a small team of HNers fresh off of our seed funding lead by Andreessen Horowitz. We’re fueled by a vision to transition synthetic biology to a fully-fledged engineering discipline. We’re building our our initial software team and need help with everything at the intersection of infrastructure, software systems, data ingestion and storage and machine learning for predicting optimal genetic circuit design. Check out some of our work at www.github.com/CIDARLAB/cello and our mission at www.asimov.io/blog

Search Keywords: deep learning, sequence to sequence learning, bioinformatics, cloud infrastructure, python, tensorflow, microservices, biotech, Boston, Cambridge

Prerequisites: * 4+ years hands on experience as a SWE or ML engineer in industry * Excitement to learn a tremendous amount about genetics, bio hacking, genetic circuit design * Excitement to autonomously improve our product with your experience in designing software and/or ML systems

Perks: * Flexible working hours, develop when you are most productive * We believe in creating a lifelong company by avoiding burnout and focusing on long term impact * We value impact over hitting arbitrary deadlines * Frequent team lunches, happy hours, and a coffee lab * Cross pollination: We’re an awesome team of scientists from diverse technical backgrounds

If you’re interested please send me an email at joe@asimov.io or apply online at www.asimov.io/careers

Quora | ML Engineer | Mountain View ML, Python, C++, TensorFlow, Spark, Information Retrieval

Quora’s mission is to share and grow the world’s knowledge. We are an internet-scale Library of Alexandria, a place where people go to learn about anything and share everything they know. At Quora, we use Machine Learning in almost every part of the product - feed ranking, answer ranking, search, topic and user recommendations, spam detection etc. Within the past few months we released a large duplicate question dataset [1], built out Quora on Alexa and Google Home [2] and linked Quora Topics to Wikidata [3]. As a Machine Learning expert, you will have a unique opportunity to have high impact by advancing these systems, as well as uncovering new opportunities to apply Machine Learning to the Quora product. As a ML Infrastructure Expert, you will play a key role in developing tools and abstractions that our other developers would build on top of.

Machine Learning Engineers: http://bit.ly/2lTPGM2

ML Infrastructure Engineers: http://bit.ly/2lzaLZz

Product Infrastructure Engineer: http://bit.ly/2mtz4fJ

And more! quora.com/careers

Please submit online at the link above and mention my HN user name. [1] data.quora.com/First-Quora-Dataset-Release-Question-Pairs [2] blog.quora.com/Introducing-Quora-on-Voice [3] blog.quora.com/Announcing-Wikidata-References-on-Topics

Quora | ML Engineer | Mountain View | ONSITE, www.quora.com/careers

Quora’s mission is to share and grow the world’s knowledge. We are an internet-scale Library of Alexandria, a place where people go to learn about anything and share everything they know. At Quora, we use Machine Learning in almost every part of the product - feed ranking, answer ranking, search, topic and user recommendations, spam detection etc. Within the past few months we released a large duplicate question dataset [1], built out Quora on Alexa and Google Home [2] and linked Quora Topics to Wikidata [3]. As a Machine Learning expert, you will have a unique opportunity to have high impact by advancing these systems, as well as uncovering new opportunities to apply Machine Learning to the Quora product. As a ML Infrastructure Expert, you will play a key role in developing tools and abstractions that our other developers would build on top of.

Machine Learning Engineers: https://jobs.lever.co/quora/4ea5b0e2-b570-439f-a3a1-1f301042....

ML Infrastructure Engineers: https://jobs.lever.co/quora/5ae871e6-12a7-40d2-829a-64041e24....

Product Infrastructure Engineer: https://jobs.lever.co/quora/37d396ed-a089-4cc2-a817-8ab65fb6....

Please submit online at the link above and mention my HN user name. Or email "%sn@quora.com" % my_HN_user_name

[1] https://data.quora.com/First-Quora-Dataset-Release-Question-.... [2] https://blog.quora.com/Introducing-Quora-on-Voice [3] https://blog.quora.com/Announcing-Wikidata-References-on-Top....

Quora | ML Engineer | Mountain View ML, Python, C++, TensorFlow, Spark, Information Retrieval

Quora’s mission is to share and grow the world’s knowledge. We are an internet-scale Library of Alexandria, a place where people go to learn about anything and share everything they know. At Quora, we use Machine Learning in almost every part of the product - feed ranking, answer ranking, search, topic and user recommendations, spam detection etc. Within the past few months we released a large duplicate question dataset [1], built out Quora on Alexa and Google Home [2] and linked Quora Topics to Wikidata [3]. As a Machine Learning expert, you will have a unique opportunity to have high impact by advancing these systems, as well as uncovering new opportunities to apply Machine Learning to the Quora product. As a ML Infrastructure Expert, you will play a key role in developing tools and abstractions that our other developers would build on top of.

Machine Learning Engineers: https://jobs.lever.co/quora/4ea5b0e2-b570-439f-a3a1-1f301042...

ML Infrastructure Engineers: https://jobs.lever.co/quora/5ae871e6-12a7-40d2-829a-64041e24...

Product Infrastructure Engineer:

https://jobs.lever.co/quora/37d396ed-a089-4cc2-a817-8ab65fb6...

Please submit online at the link above and mention my HN user name. Or email "%sn@quora.com" % my_HN_user_name

[1] https://data.quora.com/First-Quora-Dataset-Release-Question-....

[2] https://blog.quora.com/Introducing-Quora-on-Voice

[3] https://blog.quora.com/Announcing-Wikidata-References-on-Top....

Quora | ML Engineer | Mountain View ML, Python, C++, TensorFlow, Spark, Information Retrieval

Quora’s mission is to share and grow the world’s knowledge. We are an internet-scale Library of Alexandria, a place where people go to learn about anything and share everything they know.

At Quora, we use Machine Learning in almost every part of the product - feed ranking, answer ranking, search, topic and user recommendations, spam detection etc. Within the past few months we released a large duplicate question dataset [1], built out Quora on Alexa and Google Home [2] and linked Quora Topics to Wikidata [3].

As a Machine Learning expert, you will have a unique opportunity to have high impact by advancing these systems, as well as uncovering new opportunities to apply Machine Learning to the Quora product. As a ML Infrastructure Expert, you will play a key role in developing tools and abstractions that our other developers would build on top of.

Machine Learning Engineers: https://jobs.lever.co/quora/4ea5b0e2-b570-439f-a3a1-1f301042... ML Infrastructure Engineers: https://jobs.lever.co/quora/5ae871e6-12a7-40d2-829a-64041e24... Product Infrastructure Engineer: https://jobs.lever.co/quora/37d396ed-a089-4cc2-a817-8ab65fb6...

Please submit online at the link above and mention my HN user name. Or email "%sn@quora.com" % my_HN_user_name

[1] https://data.quora.com/First-Quora-Dataset-Release-Question-... [2] https://blog.quora.com/Introducing-Quora-on-Voice [3] https://blog.quora.com/Announcing-Wikidata-References-on-Top...

Thanks! Just fixed

Quora | ML Engineer | Mountain View, CA | ONSITE | www.quora.com

ML, Python, C++, TensorFlow, Spark, Information Retrieval

Quora’s mission is to share and grow the world’s knowledge. We are an internet-scale Library of Alexandria, a place where people go to learn about anything and share everything they know.

At Quora, we use Machine Learning in almost every part of the product - feed ranking, answer ranking, search, topic and user recommendations, spam detection etc. Within the past few months we released a large duplicate question dataset [1], built out Quora on Alexa and Google Home [2] and linked Quora Topics to Wikidata [3].

As a Machine Learning expert, you will have a unique opportunity to have high impact by advancing these systems, as well as uncovering new opportunities to apply Machine Learning to the Quora product. As a ML Infrastructure Expert, you will play a key role in developing tools and abstractions that our other developers would build on top of.

Machine Learning Engineers: http://bit.ly/2lTPGM2

ML Infrastructure Engineers: http://bit.ly/2lzaLZz

Product Infrastructure Engineer: http://bit.ly/2mtz4fJ

Please submit online at the link above and mention my HN user name. Or email "%sn@quora.com" % my_HN_user_name

[1] https://data.quora.com/First-Quora-Dataset-Release-Question-... [2] https://blog.quora.com/Introducing-Quora-on-Voice [3] https://blog.quora.com/Announcing-Wikidata-References-on-Top...

Quora | ML Engineer | Mountain View

ML, Python, C++, TensorFlow, Spark, Information Retrieval

We are looking for experienced Machine Learning engineers, ML infrastructure engineers and product infrastructure engineers to join our team. At Quora, we use Machine Learning in almost every part of the product - feed ranking, answer ranking, search, topic and user recommendations, spam detection etc. As a Machine Learning expert, you will have a unique opportunity to have high impact by advancing these systems, as well as uncovering new opportunities to apply Machine Learning to the Quora product. You will also play a key role in developing tools and abstractions that our other developers would build on top of.

Machine Learning Engineers: https://jobs.lever.co/quora/4ea5b0e2-b570-439f-a3a1-1f301042...

Software Engineer Product Infrastructure: https://jobs.lever.co/quora/37d396ed-a089-4cc2-a817-8ab65fb6...

Software Engineer ML Infrastructure: https://jobs.lever.co/quora/5ae871e6-12a7-40d2-829a-64041e24...

Please submit online at the link above and mention my HN user name. Or email "%sn@quora.com" % my_HN_user_name

Quora | ML Engineer | Mountain View

www.quora.com/careers/software_engineer_machine_learning

ML, Python, C++, TensorFlow, Spark, Information Retrieval

We are looking for an experienced Machine Learning engineer to join our growing engineering team. At Quora, we use Machine Learning in almost every part of the product - feed ranking, answer ranking, search, topic and user recommendations, spam detection etc. As a Machine Learning expert, you will have a unique opportunity to have high impact by advancing these systems, as well as uncovering new opportunities to apply Machine Learning to the Quora product. You will also play a key role in developing tools and abstractions that our other developers would build on top of.

Please submit online at the link above and mention my HN user name. Or email "%sn@quora.com" % {my_HN_user_name}

Quora | San Francisco | ML Engineers

Quora's mission is to share and grow the world's knowledge. A vast amount of the knowledge that would be valuable to many people is currently only available to a few — either locked in people’s heads, or only accessible to select groups.

Quora is looking for ML engineers to help us reach our mission. My team focuses on ranking: the recommendation algorithms behind our read and answer pages. Check out our VP of engineering's recent talk at RecSys www.slideshare.net/xamat/recsys-2016-tutorial-lessons-learned-from-building-reallife-recommender-systems

we're a company of machine learning focused individuals interested in really opening access to knowledge. Interested? Apply online at www.quora.com/careers and mention my HN handle!

(python, c++, machine learning, recommendation engines :)

Take a look at the challenge homepage, http://physionet.org/challenge/2016/

tl;dr ECG is much more accurate but requires a careful, controlled environment. If it's possible to accurately predict heart abnormalities from sound, cheaper, easier to run screening tools can be developed for at-home use.

All of the data can be found on the physionet site http://physionet.org/physiobank/database/challenge/2016/

Hey thanks for the great questions!

(1) The NN uses two convolutional units and a fully connected softmax layer. Relative to Inception V3 or highway networks, this is _not_ a very deep architecture. I was looking for a balance between accuracy and training time (trained on my MBP).

(2) I looked into other neural architectures (LSTM and several fully connected) without much difference in performance. If you take a look at the physionet google group, there are a number of other methods evaluated (logistic regression, SVMs, etc.)

(3) I did vary hyperparameters and saw a dropout of ~0.45 and frequency cut-off of 4Hz performed the best for this specific architecture. That said, I imagine the best performing features would be a concatenation of the output from several filters across a range of thresholds. Then the burden of deciding feature importance falls onto the learner.

http://arxiv.org/pdf/1507.06228v2.pdf http://physionet.org/challenge/2016/#forum

The ML community has techniques for building methods to address low signal to noise, class imbalance, noisy labels and smaller sample sizes. I definitely agree, all of these are issues in medical datasets. Part of the exciting challenge at the intersection of medicine and machine learning is around scaling data collection while respecting patient privacy.

Thanks! I definitely agree that collecting these signals is difficult to scale.

I definitely agree! The challenge is collecting a large number of heart recordings from mobile phones, along with professionally diagnosed abnormalities. That's one reason this physionet dataset is so valuable.

Check out http://avisingh599.github.io/deeplearning/visual-qa/

Recurrent Neural Networks. They're so cool. Used in everything from creating chat bots to describing pictures to machine translation. Bengio and Goodfellow have a preprint book available https://goodfeli.github.io/dlbook/

Really cool, thank! The `types` seem to be a good way to add context if you know, a priori, the type you're looking for.

Google definitely fuses user data into their knowledge graph. This is seen in Freebase's `g.` identifier [1]. I'm curious if they'd influence their publicly facing API algorithms using that data.

[1] https://groups.google.com/forum/#!topic/freebase-discuss/_8x...

Completely agree! I'm curious if the `query` parameter in the API performs well on long queries (with context) or if it needs to be focused to a single entity's name

I'm curious how the knowledge graph API performs disambiguation without any context. E.g., if you search for `Apple` will it return the company or the fruit?

Google's knowledge graph was in part based on Freebase, a large open knowledge base written by Metaweb. Google acquired Metaweb, continued to grow it's triple extractors [1] and eventually shut write access to the graph. Wikidata is slowly extracting information from the last public version of Freebase to grow out their own knowledge base.

[1] http://www.cs.ubc.ca/~murphyk/Papers/kv-kdd14.pdf