HNHacker News
TopNewBestAskShowJobs

alexcnwy

785 karma · joined May 14, 2017

Co-founder / CTO AiSupervision (YC W22)

YC Badge: 0x0c51bf0090235f2604af81df021023a3d62aa4d3

E: alex [@@@] numberboost.com

L: linkedin.com/in/alxcnwy/

X: @alxcnwy

Consulting: www.numberboost.com

Here is a vid of one my talks on deep learning for computer vision: https://www.youtube.com/watch?v=X4Q6C915sUY

-----BEGIN PGP PUBLIC KEY BLOCK-----

xsDNBGUfNa8BDAC1U6epAyxNbnBiVVa/5xg/VqviJmBvAFw7IMuRTXXpmmnUdPehwFsZTIsVxOQs jSZgB58d7V7Ps0NyDbpThGdV6D/Rs9O0RQ7NzBhPWtgXMjL05CMzQQKwAQwYiOXoMmdIFx+dDs4Q sEuTwhN7ZVfq1wCwvKaGaIa9YNs+84NP9nC4+0i1mb3kY4YFwsRUuiX1UuKaSVkF47ZGAdm+QyCz 4r12/eiRlfyR4Tn2MoKTcWjWcpON0Jt2c6NZAmae1ofBQd11AdenItwMcIz/YB388I+WSUtXal6i Ou1kHfkZD0cVBnKWSxbbdkTvlJwOTROq1PqfUxoJ7lNDse9t4UqWSLnxcChAw7G6cusvemEfyUBs bpbehD756bwrQDD4bc1GX4wHG7iERDrraUHEado+D4hcZJeE3hQ+hLQLbVUkfIOo8QANu/nEc533 utazWsUdzPB9ZhNXGESBU6FD1Dq3T7F88GQwgLhMWpLyw2bVIrHE1K+VFlWKeeTuS6LUXDcAEQEA Ac0AwsD6BBMBCAAkBQJlHzWvAhsDBBUICQoHCwkIBwMCAQQWAwIBAh4BAheAAhkBAAoJEL0wgBjJ Evk4fY8MAKEwfG6n8MSCdH/PYJdZCorgFe3Si+5XUAKuRVzXpIihwz+imuaNqabSvKt3BwvAJ3WQ F7xbWCSveIeTKv893gv5kglFi0pxQhCd2kpWY96O/zKThXZGbBQG19/276M0V9PnubnO0EOpNzxi QYjnU4UxmH32mjwx42Xb+/44Ird1iBW6TU4oE87iugjqbMREvsuRerur/jViUhCCkAwohM4OWTP6 HvHj57KH01wcqWROyiTj2amdV+lpizzRyvF9cC68p5zakGG7tyJ7fQMXIhgV72hj37mMDSq/qcsB lB3PFjc8mu/9zKwWlVNhV3G+8fFZ+dTuNvdsP0v2XbLqrONMYFrbnH3lsG/SjTzP0Ea5Mt3Wq8JV UQvA70xlS7YaI8juAbTYLFmssNVDQ77G+gMVXiKxRtPNvH4sc6HOsemsDpA3Rl86iY5MGDexT/oH 3FxslNSHGCy77WPRe8HsipoWLiWRiHuQqc5afsMExtgnoUIpU6r3WPG5Be00Pg0dxs7AzQRlHzWv AQwAxdgbC3umULrQGh423QVZZh+vwv5k9K2c/67JzuErFo02ld+9+0B23xbulUSw9igz1udmBFtW sU8212O40TMDACOdxMljYhB99zVnoo1zW17wce+ZrR/F+Qgdc8cJ0mb+V66/0VFzdxgVMEwCKVS+ TweUhrDBwnxVAr+zTPvTBHohIq9S2Md4+r5fM5uhy67WQFJ+nYe8mVEVHhG7NETOCSqVx1WCF/vs +4d5aUTZ/A8OVZxiEe2PlxeWeH4FVYsQe7qAroM0nkawtSPMGcHPfsM3R49x2XEiKeSssyXNiypX mIc8Z2MiIt8Yu264C8BXllL9LVKLgoSdgs/zoDK0VoLthLh+PNrz/FUsU+lvQaPUVL9MywP4FWyt K/Y82ObuUDglLs74HsT1y7jPV0G2HqmHe9jkdvFsFe6pqIILoOEucMyvYsrTfwFlAHuYQxjjCcIm L95F+AZQLMoD0gyTKuIlOvfX65bWSNp+5msPmWHP98eFvwSWvwhYf8CfxpFtABEBAAHCwn4EGAEI AagFAmUfNbACGwzA3SAEGQEIAAYFAmUfNbAACgkQDnm6M0ernGu5qgwAw0Xss6TGEWIkuBKgTkpl aN3iKETevBhJ+wp7uPeUnEZZdUwIEnZI4Vy7yiRUmhxH5BF78xueE+qOdiHVGzeLeEUj/mg6y1Mf LL5peoyjZLWOULOUec5vLKpLtUKuWrIoaZmQjFoJerWDpyLb0j/OpdSf077hrvNtK+a7pCGl++GT IFqiPHIibrsC02zLy0Oc4PjJgHI02vGhJLoEnml3dbuG/QoE1RCsnKY52bjA9qrKklS4ymwURpN6 jODnCTjpJZv+6wEDbf+9ks8S+XUfQyl3B+s+6Wp9SdSjIMsewQWiZUAnro6s72PdoBDPu8KX4N5/ itJUkqfKRtJDgU8geKgbnqy5Gw1CnDfs2ER1GlNoFFdsgGeSzNTmu4hzrtS9JcemkmBsYnxNLMjD //RWR4xiS6mEeZtEHj5/+8p4UqIWHIn0mXDWxwpZx0vsgtceoGAtS+KPuZIGHJSBkhnBkIg48mq5 oHGABF3W8s78LQT1F6Wf+r1TNARxXhLKRAfVAAoJEL0wgBjJEvk4xhcL/iZTPV+/mu5N3VA5zqYc uzXt4Z599ki57YJ0/ciZIlbjXog2Sqso78pxEw3PfBffJznamyqbchUiarjR5CMCZbTPJ7vJVPoF pPAQCRLfAVop6Jdq3fyAQMURFkgpMwfmSzZ3Fri/4TP4DRCRAEjzvCchfbTGI1H8ifz3bAoAFlG/ b2ttZug0baKb2gzFfsG+XPr3JfXG/at+95M1wbO3Kiw2y8y5mct4xwRUnNnkuEdoswcgeIe+cvNm JS3mxUL8PdmOLY+Wk1+tGjbgBiiH+6HE/uSteXYPDFklq5AtJ4/62nddHiZ4uisK+Pxy8TnToCaV 7Wbg0V2l6nJPPBmWQqgMQtPMrD0Blr5FkVND/+4cBH8dB2a7yi/MmJqaydxlc7hrKR5dvnrIRNJg WG5gq0Vn5z4FLr1Crp4uu5ymUWF/mdxSa4hTL1kboRfrL0GTEKB8p42GgJJdr5evHlkFv/GEY/MS sKod3avN+QOFXfpvRxbXssHClpuFunAPU+QQisXEmARlHzWvAQwAtVOnqQMsTW5wYlVWv+cYP1ar 4iZgbwBcOyDLkU116Zpp1HT3ocBbGUyLFcTkLI0mYAefHe1ez7NDcg26U4RnVeg/0bPTtEUOzcwY T1rYFzIy9OQjM0ECsAEMGIjl6DJnSBcfnQ7OELBLk8ITe2VX6tcAsLymhmiGvWDbPvODT/ZwuPtI tZm95GOGBcLEVLol9VLimklZBeO2RgHZvkMgs+K9dv3okZX8keE59jKCk3Fo1nKTjdCbdnOjWQJm ntaHwUHddQHXpyLcDHCM/2Ad/PCPlklLV2peojrtZB35GQ9HFQZylksW23ZE75ScDk0TqtT6n1Ma Ce5TQ7HvbeFKlki58XAoQMOxunLrL3phH8lAbG6W3oQ++em8K0Aw+G3NRl+MBxu4hEQ662lBxGna Pg+IXGSXhN4UPoS0C21VJHyDqPEADbv5xHOd97rWs1rFHczwfWYTVxhEgVOhQ9Q6t0+xfPBkMIC4 TFqS8sNm1SKxxNSvlRZVinnk7kui1Fw3ABEBAAEAC/90T2K+QPDMAklIaiEpG10sU7YRbDhzOzHu I40weRVncMrtotGtCavlwHl+zzrlcOzqsDjag4ZLiFt8711TcRyvuDgnlUf43Eswqvf0/vqZdnPF Lgl+OPc2WpWdr0J5/MrPLTX0EqkPf2YbM2Q3xLvuQVeKBphyot264EQCT0Utp5CKt3TeN+3ccBJp 45L4Hid3A2GjQeU+p+Ala852Aq0Zdhm+GAR0TlciY+xABgpH9XkgBYKsduEhy+89ixK0VDrPe2yy eiUAkQjGoDISoi4NpgnkA5g6YntBLTtde4Fk6AvQeEjHWjqawKclDrtXeuFyKHmj1Nn3uqOHTImJ AJwFbab23dl2mEYeakcL8ihnpvuggcakAO1rgXRWVmibItjdPWw1uMo+ugXAwm8irW/vAQe5uLMH eLAD2lKci/gGp8/e2rcv1eTKjtfq+L4VH8BoNWmN6e38EBox1Fai5hRMtRtWOdlBSuCP5u2K+sg6 xfaCvm2opBDDdkQYQ3c/dIEGAOItRO0ezZV7Fy1zCXzKz5JGLHblm+2SdTSJKJBaJzt4OIWhOpKG jmWIAeOMk0hV55PNarieoX6aNwm9wnEtoB7hbp+fmq994hjzkm7/irtwWLH33d+XUNlmGjj3Pvua Ri0sSD5Uoa7gxfizekGN7xH3GeWUwEuOSHAi1E0RICfMH3KV5z5ezVpFbq+GtDxuFrOcXmEUh8k1 BL0XCyhIwUNlmBPGs5TdswB5ZfPpLcDTQoqTAQ4pKVfoOMoqYkENVwYAzTxyJ2iEZSUyc6J30BFA oWyBlUcJo5T2q23aWA2JZTMVYKNKNomoZsJ3F3G8wpDriFLFgEjwjp0CQpnPrt/MSd3SgiZkTP8L SBkK4yKemVsjb2fInHgrU334WUg1cLFaJ9zRf1qVJk6jo60rSmp81fsWNQpMK4OcU85j34uw8h5F dIQnUxcjRwVCQj5umWGYQrebF0qj1xLSCtA5D6pdzPZKZo+4aHU6ELPlW0Sm4T2braOXBsBkdRMk i0SpMPwhBgCY/5Hoj3z12zIOSqRMzrfzKbNJTqyz+8IHtWOm/6/RTlA1m9nR4l8dKWi/A0YRbZ1Q fhzPI8L4To3Ta2Rb1vPPPZF67biMZs/YVC3Vd6ZdaT3aXjswOtKaqNxYJsur37oCUSIPBmsGr7ys Itif0oO7dsJ3bwq4YErDSaiWjl9RmGsZpr0hPBHQ4snLyHRgmwPnr5IivIA0o83FFCM6xv1R3TOS PSG4XRH8D2MLrj5GU6oZDI4uXFNz1bUYesjOxK3RNs0AwsD3BBMBCAAhBQJlHzWvAhsDBBUICQoH CwkIBwMCAQQWAwIBAh4BAheAAAoJEL0wgBjJEvk4eo4L/2v0fEQxSdYwSHnuH9htH/EJZNadRnJc 6UjUv1Tg2XAxm3W5WWF9DCTufjnpEYGA0aT3fsYiAcBSqDUIe/r4d83K6BnmbzDHqnD+L03HRPIq xsmiP7u2mxoxnjxEjuzILQ9TemRNkcQwWqkRK7RNsJLcOdvMH1ydWRmYaDpKYsqd127b8qR6w7tx ro2JduFrV/LYEZt2anKUGZ0Q5aWPYHsmlM+8BuIoCjPewPOHgFLk9RFRLLuR9AlvMCU5tNToVJwr NM9m6yf4yKUAW2oVfPv0E79z9Lsu32B/dJAIweTeYxymRUDK+4/wya7BFdesUZ9TI5YMs4pSOaMx UZbcEIYs0Ji6BPR3q6Dnaon1rQxrulYRFEfUfb6XIOjCDSyLjI84chsU7asbeBpVy5ER9PxYhdaM gi06yK6KBzX/llSIc5sK9eQpyB0rAI3ffZfB5iOcgX+X1eREm0y3m46dI7nSXtgIUiIlGtLKf6yZ ALlQLXSqS+19rHL7aWuZ2I8BfcfEmARlHzWvAQwAxdgbC3umULrQGh423QVZZh+vwv5k9K2c/67J zuErFo02ld+9+0B23xbulUSw9igz1udmBFtWsU8212O40TMDACOdxMljYhB99zVnoo1zW17wce+Z rR/F+Qgdc8cJ0mb+V66/0VFzdxgVMEwCKVS+TweUhrDBwnxVAr+zTPvTBHohIq9S2Md4+r5fM5uh y67WQFJ+nYe8mVEVHhG7NETOCSqVx1WCF/vs+4d5aUTZ/A8OVZxiEe2PlxeWeH4FVYsQe7qAroM0 nkawtSPMGcHPfsM3R49x2XEiKeSssyXNiypXmIc8Z2MiIt8Yu264C8BXllL9LVKLgoSdgs/zoDK0 VoLthLh+PNrz/FUsU+lvQaPUVL9MywP4FWytK/Y82ObuUDglLs74HsT1y7jPV0G2HqmHe9jkdvFs Fe6pqIILoOEucMyvYsrTfwFlAHuYQxjjCcImL95F+AZQLMoD0gyTKuIlOvfX65bWSNp+5msPmWHP 98eFvwSWvwhYf8CfxpFtABEBAAEADACguxgFtTgCIDNO9LsHxv/BOv71AO4N5jpFcsAbZc02rhTp n/NdexrX1W6RMFRAN5sd/bJg2b/Nnxhj1m1g7/uBEm5rYF1wXwunWejPI/HTCod3WPvVrZmN3yzm UY7GM8xwedT2fiC7YYJdUXL0FxfhZrwgzNstYQtDh3Bom7Hs0je3UQ6SdUPxGdaIO+kva+Q+L4cT /iGXwUrRugAHz9o/kixK3EorqAz4sDBP+JLL94NixADcpc5hJtWlIGS/AZE91ufRKPjybrppgiGe HR7GliXYc4fgcXlPs/9uWgfDgf2biRDTQ73DFIAWqRh42WEvnUs0avIKgKdkoIOmUb0mZT5jGxXe 5BQDjrHm9RvAyuZ2nnZJVWDIgRKOR1azx0z7PGNL0qyEcJ0VydzLKjrzqFFJOdISRgPXUl76sQiF rM1sL4fWbgdogINwSAblnKg2sJuIapwN9IAFglNqrZXBfIIlYYYW1K/EUG/zpLxR6RzJnUXuo8d3 C0JEEsiSIRUGAOcNGH3OEdsogHsTcV4dp1bzcm4XA9TY4x2P3UNwS/XiEARj0TmlHi0J6Q7AjHk5 65KivwjSwWTfe7XOg6oVUoobbTTn9jXmveTac8rZfbxasvHfQqGiEPFEaxyWAjjhJEBIp7twHu2e bS2IcqKxsN/48d3K1M8eBriybqF7gkPghnxfcmRnYIcuZ6/7uSDO/FplHyl8Z19DTCVHbS5fEyck TQlllEPfnmEQqo1NZSzLfPWtzsS15Dw+A2kSLK6hSwYA2zUTQkcMSrHY4/snm1dlNy3FWL6361OD 2hM4xYDYymig1GfTw4rD7SD2Ni2OeKms0Y+tlRJPiOqMNpo+XvlFRqFW5Iro2BRg1Ag6I/2AM+oQ BEe0J5EKl52sMX63sGxVcCn20Rr8EJ40sdSXUj7bw/wSlBUTJpAurzLc5K+Ks4wu4YfrJRXGOSwK murvBs62ZmQb2BWBGr4StWPhEcURRyVLIgJL7GavFH+Td3TvB0mCw5Ws+iyWfC40pX4hI50nBf9E ZQHXYiL6eYpuCE3hor/955qw8HyvrNDK9YHI9sv77uEz4t+DvHbrIN/oPQ7wuE05cYBBdSrVe1LK Tnue9vY9FkDLSI9x2Igdii/DP7S+WST40xTr8xrHR2O8n+IdvXLgu99PsvP6OdKTxxVSnt4pvzh+ EX2r+CqxF8cwUYdrUJLFoEowBdhkTM9h41duWz7YvtPJ02f59GI5Ev6dT8UJRCWuj53TPwEh5hXO dF8rp+EJACx+yVUDksnovhT6VXniF8LCfgQYAQgBqAUCZR81sAIbDMDdIAQZAQgABgUCZR81sAAK CRAOebozR6uca7mqDADDReyzpMYRYiS4EqBOSmVo3eIoRN68GEn7Cnu495ScRll1TAgSdkjhXLvK JFSaHEfkEXvzG54T6o52IdUbN4t4RSP+aDrLUx8svml6jKNktY5Qs5R5zm8sqku1Qq5asihpmZCM Wgl6tYOnItvSP86l1J/TvuGu820r5rukIaX74ZMgWqI8ciJuuwLTbMvLQ5zg+MmAcjTa8aEkugSe aXd1u4b9CgTVEKycpjnZuMD2qsqSVLjKbBRGk3qM4OcJOOklm/7rAQNt/72SzxL5dR9DKXcH6z7p an1J1KMgyx7BBaJlQCeujqzvY92gEM+7wpfg3n+K0lSSp8pG0kOBTyB4qBuerLkbDUKcN+zYRHUa U2gUV2yAZ5LM1Oa7iHOu1L0lx6aSYGxifE0syMP/9FZHjGJLqYR5m0QePn/7ynhSohYcifSZcNbH ClnHS+yC1x6gYC1L4o+5kgYclIGSGcGQiDjyarmgcYAEXdbyzvwtBPUXpZ/6vVM0BHFeEspEB9UA CgkQvTCAGMkS+TjGFwv+JlM9X7+a7k3dUDnOphy7Ne3hnn32SLntgnT9yJkiVuNeiDZKqyjvynET Dc98F98nOdqbKptyFSJquNHkIwJltM8nu8lU+gWk8BAJEt8BWinol2rd/IBAxREWSCkzB+ZLNncW uL/hM/gNEJEASPO8JyF9tMYjUfyJ/PdsCgAWUb9va21m6DRtopvaDMV+wb5c+vcl9cb9q373kzXB s7cqLDbLzLmZy3jHBFSc2eS4R2izByB4h75y82YlLebFQvw92Y4tj5aTX60aNuAGKIf7ocT+5K15 dg8MWSWrkC0nj/rad10eJni6Kwr4/HLxOdOgJpXtZuDRXaXqck88GZZCqAxC08ysPQGWvkWRU0P/ 7hwEfx0HZrvKL8yYmprJ3GVzuGspHl2+eshE0mBYbmCrRWfnPgUuvUKuni67nKZRYX+Z3FJriFMv WRuhF+svQZMQoHynjYaAkl2vl68eWQW/8YRj8xKwqh3dq835A4Vd+m9HFteywcKWm4W6cA9T5BCK =Iwr2 -----END PGP PUBLIC KEY BLOCK-----

submissionscomments
alexcnwy··on Ask HN: How to speak like a leader, not like an engineer?
toastmasters - especially the improv "table topics" activities - has been indescribably valuable for me.

It helped me go from being too shy to give a presentation in front of one person to giving talks to hundreds of strangers at a time.

Pro-tip: you can attend the first one or two meetings of each toastmasters group for free so if you're a broke student like I was at the time, just rotate the groups since there are several in each city. Also universities often have great toastmasters clubs.

alexcnwy··on Teen Becomes First Hacker to Earn $1M Through Bug Bounties
The third party doesn't know about the vulnerability. Company C posts bug bounty B in contract. Researcher X discovers vulnerability. Validator Y confirms the vulnerability and X gets paid (1-f)B where f is validator fee.
alexcnwy··on Polar as a Personal Knowledge Repository
I've tried everything and I really like Dynalist (or any other outliner) as a personal knowledge repo / place to store notes and ideas.

I find ideas do tend to be quite hierarchical and you can link between nodes if need be.

alexcnwy··on Show HN: Exoplanets Data Visualisation Using D3.js
Very cool, great job! One bit of feedback: hover interaction doesn't make sense on mobile. Can tap to trigger hover as a workaround and use media queries to change instructions instead of telling user to hover.
alexcnwy··on Teen Becomes First Hacker to Earn $1M Through Bug Bounties
The company posting the bounty. Third party verifies the bug. Why sarcastic?
alexcnwy··on Deep Learning to Federated Learning in 10 Lines of PyTorch and PySyft
I agree - it's a problem worth solving.

Re: not having data to QA model, you can use the distribution of the generated labels to inform model updates. Alternatively you can get labels at the edge using a local edge interface then use those.

alexcnwy··on Teen Becomes First Hacker to Earn $1M Through Bug Bounties
Sounds like an actual use case for staking - bug bounties on teh blockchain!
alexcnwy··on Show HN: I made a site that lets you stream any torrent
Any suggestions on how to do that? Asking for a friend
alexcnwy··on Deep Learning to Federated Learning in 10 Lines of PyTorch and PySyft
I 100% believe that federated learning is going to be the new standard process in the future for many applications. Sending the model to the data instead of sending the data to the model (in the cloud) just makes so much more sense from a privacy and bandwidth perspective plus you can use the user's computational power instead of your own.
alexcnwy··on License Plate Detection Without Machine Learning
This approach fails e.g. The morphological operations you need for an infrared night time image with washed out white is different than what you need to detect the plate in the day time etc.
alexcnwy··on Ask HN: Before We Spend Millions, What Do You Think of This Blockchain Use Case?
A related company that uses the blockchain in an interesting way for DRM (which I have my own views on) that was in the same Cape Town startup program as my startup: https://custostech.com/
alexcnwy··on Github restricts public Faceswap repo to logged-in users
This is troubling in the context of OpenAI deciding not to release their code and dataset for fear of it being put to bad use. It's a tricky topic but I get nervous at the idea of research being censored.
alexcnwy··on Ask HN: How are you getting through (and back from) burning out?
Be patient, it takes time for your body to recover from bouts of sustained exertion...
alexcnwy··on $190M missing after crypto exchange Quadriga CEO dies
Paywall but can read article if you stop the page from loading before the modal pops up
alexcnwy··on Ask HN: How to found a company as a single founder?
If the words of some random person on the internet can dissuade you from being a founder then you're not cut out to be a founder.
alexcnwy··on Ask HN: How do you keep track of your creative thoughts?
Dynalist
alexcnwy··on How to DIY a Product Launch Video with No Experience, and for Free
Very cool and I think the product and landing page are gorgeous!

One bit of feedback on the vid is I think it could be better timed to the music - the text zooms should be on the beat breaks.

alexcnwy··on What Kagglers Are Using for Text Classification
thanks for the tip!
alexcnwy··on What Kagglers Are Using for Text Classification
CNNs are usually much faster than LSTMs.
alexcnwy··on Artificial Intelligence Creates Realistic Pictures of People
I legit registered aistockphotos.com when I first saw that paper.
alexcnwy··on TensorFlow Lite is for mobile and embedded devices
you could use a pretrained object detection model with some lightweight logic built around it (e.g. send you a slack notification when a human object is detected in at least 5 consecutive frames between these hours) but you might also want to find-tune a pretrained model to work well given your camera's angle, lighting conditions, etc.
alexcnwy··on Facebook open-sources a speech-recognition system and a machine learning library
Totally agree - it's hard to say which sequence architecture works best for your problem (are there long term dependencies, do they exist at multiple levels of scale, etc) and dataset size.

Convolutions are cheap to compute and can be more efficient on smaller data but it's also possible that a CNN outperforms when you have a small dataset and an RNN when you have a larger dataset.

alexcnwy··on Machine Learning Trick of the Day: Instrumental Thinking
Shakir is a force of nature. He is one of the organizers of the Deep Learning Indaba - an incredible effort to strengthen machine learning in Africa. Unfortunately the 2018 videos aren't out yet (Shakir gave an amazing talk on deep learning fundamentals and some of the tricks from his blog) but everyone should be aware of Shakir and the Deep Learning Indaba: http://www.deeplearningindaba.com/
alexcnwy··on PracticalAI – A practical approach to learning machine learning
Colab is awesome but I've found that GPU memory allocation can be a bit unreliable at times. It's advertised as providing you a GPU but in reality I think you're sharing the GPU with other machines which can lead to out-of-memory issues fitting models that you don't run into using a dedicated GPU instance
alexcnwy··on Ask HN: What are some hacks of real founders who did things that don't scale?
You can use the model's output probabilities to optimize QA routing - any cases with less than 90% confidence to humans but save humans doing the cases that can easily be done by models :)
alexcnwy··on A Gentle Visual Intro to Data Analysis in Python Using Pandas
Neural net universe is in Python and you can use Python to build production pipelines.
alexcnwy··on Raster Vision: A New Framework for Deep Learning on Satellite and Aerial Imagery
Very very cool! The thinking behind improving the data preparation phase to avoid a mess of scripts that reinvent the wheel is so on-point, especially for satellite data where preprocessing can get messy.

I'm looking forward to trying this out - bookmarked for my next satellite imagery project :)

alexcnwy··on Ask HN: What did you learn the hard way?
Sounds awful! I've been working my butt off with some friends on a system to extract data out of scanned forms and documents (incl. handwriting) and I'd really appreciate hearing your thoughts about it. Couldn't find your contact deetz so please send me an email - address in my profile :)
alexcnwy··on Ask HN: What things have richly rewarded the time invested in mastering them?
Also remember businesses are taking risk - they may fail in making a profit but your income is (barring them going bankrupt) risk-free.

Profit is the risk premium.

alexcnwy··on Practical Deep Learning for Coders
Same here! Still busy with my MSc thesis though because I'm too busy applying some of the other stuff I learned from Fast.ai on other projects ':)
← PreviousPage 6 of 10Next →