Daniel McAllister

[John Lambert @jlambert_]

Impressive progress on correspondence -- one of the oldest and yet still hardest problems in computer vision -- using test-time-opt/NeRF. tldr: find mapping from 3d points in per-frame 3d coord. systems to their unique global trajectory index (i,j,k) https://t.co/hvoueoxF2b

[Michael Saylor @saylor]

In the first quarter, 2683 people completed the #Bitcoin for Everybody course offered by @saylordotorg. It is available worldwide on web & mobile devices, only takes ~12 hours, and is completely free.
https://t.co/fdHVxBX8TI

[Crypto Dan @cryptodan19]

I've been in Crypto since 2017 and automated my 7 Figure Investment Process to 20 minutes/day

Literally scrapped the entire internet to find this data.

You won't see this info anywhere else on Crypto Twitter.

Like this tweet and reply '🔥', and I'll DM you the doc for free.

[Justin Welsh @thejustinwelsh]

Every piece of advice I could think of after 4 years as a Solopreneur.

1. Pessimists are often right, and optimists are often wealthy.

[Anthony Goldbloom @antgoldbloom]

Been spending the last few weeks speaking to data scientists working on demand forecasting. Some interesting things I learned. ���

[Daniel McAllister @dmcdata]

@Airlink_UAE I paid to ship Dubai to Northern Ireland door to door. The cargo has been 3 months in Rotterdam I've now been asked to pay for storage. Please advise why this took so long to be disclosed?

@dubai_consumers

[Maialen @maysotes]

@Airlink_UAE I did pay for a service door to door from Dxb to NI, now I'm not only waiting for my shipment since March, but also I am asked to pay extra 360€ to have it delivered to me. Please explain because this is absurd and outrageous.

[Daniel McAllister @dmcdata]

@Airlink_UAE I paid to ship Dubai to Northern Ireland door to door. The cargo has been 3 months in Rotterdam I've now been asked to pay for storage. Please advise why this took so long to be disclosed?

[Jeremy Howard @jeremyphoward]

Are you ready to embark on a deep learning journey? I've just released over 6 hours of videos and the first in a series of notebooks showing the thought process of how I got to #1 in a current Kaggle comp.

Follow this 🧵 for updates on the journey!
https://t.co/4NZ425XAO8

[Jeremy Howard @jeremyphoward]

If you want to lift your object detection game, this thread is a gold mine!

[PlanB @100trillionUSD]

New #bitcoin ATH 🚀🚀🚀

[Santiago @svpino]

Designing, Visualizing, and Understanding Deep Neural Networks.

• UC Berkeley.
• 100% Free.
• Spring 2021.

66 YouTube videos: https://t.co/u7HdAWxLgC

[Aman Arora @amaarora]

I've been working on Object Detection for the past few weeks - and I am proud to announce "The Annotated DETR" !!

https://t.co/iZFbEm0F0K

In this post, I try to explain all the magic that goes on inside the architecture.

1/n

[Philip Vollet @philipvollet]

Update for Deepface a lightweight face recognition & facial attribute analysis framework

@serengil

It's a hybrid face recognition framework wrapping state-of-the-art models: VGG-Face, Google FaceNet, OpenFace, Facebook DeepFace, DeepID, ArcFace & Dlib

https://t.co/tiZ6VUBYzK

[François Chollet @fchollet]

A good model isn't a description, it's an explanation. An accumulation of observations does not explain anything.

[Vlad Haltakov @haltakov]

Mastering your Machine Learning Interview 🧑‍🏫

I've summarized some great resources for you that will help you with your Machine Learning interview.

Read below 👇

[François Chollet @fchollet]

Programming is about aligning what the code should do, what you think the code does, and what the code says.

Intent, mental model, syntax. If any of these pieces is out of sync, your code doesn't work.

[François Chollet @fchollet]

Usual reminder: when I've been saying for the past 5+ years that deep learning is interpolative, I don't mean it does linear interpolation in the original encoding space (which would be useless). It does interpolation on a low-dimensional manifold embedded in the encoding space.

[François Chollet @fchollet]

A critique of ML you sometimes hear from non-ML people is that ML, unlike Physics, lacks certainty, precision, and exactitude. That is by necessity: ML is a fuzzy way to deal with fuzzy problems.