You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
I disagree. It's difficult to understand and fix bias through #AI algorithms for #DeepLearning These are highly non-linear blackbox models. they amplify biases. many works show that trying to fix superficially is like putting lipstick on a pig. We need fresh thinkinghttps://twitter.com/ylecun/status/1203211859366576128 …
In a recent work we report an intriguing finding to detect bias : assess hardness of different samples for #DeepLearning model. It's a first step. Using it to fix bias is much harderhttps://twitter.com/animaanandkumar/status/1203090855097057280 …
More importantly our work shows that #DeepLearning model is deciding which samples are hard for it to classify and introducing bias. Here I use bias to mean disparate treatment not statistical bias. Model leaves harder example with worse accuracy and more vulnerability to noise
So which #DeepLearning model you choose changes the bias introduced. We show that older models like Alexnet are worse compared to newer models like resnet. So that's a good thing. @BeidiChen @Anshumali_ @animesh_garg @jankautz @NvidiaAI
It's important for our #AI leaders to acknowledge that #DeepLearning makes it harder to deal with bias. Models themselves introduce bias. It's important for our leaders not to be so dismissive of deep work happening in this area. They should listen and learn from others.
Given Bias itself is essentially decision of good/bad to someone or something(w/ implied opp for other), whether an algorithm decides or human decides, the decision remains biased as long as the decision is based on exclusion of someone or something. Agree?
I think ML models work because they learn based on biases. The problem arises when we use ML to decide for humans, like how much credit one must get. A fat tumor will not complain that ML is biased against it to tag it as malignant. However ... (1/2)
That’s a very fair point on DL and bias . But isn’t it still harder to fix bias in people comparatively ?
Just answered your question as an addition to my thread
I agree with you. We encountered that bias at Amazon in certain datasets and projects. I remember having the same arguements on the PE forums there then, with some people claiming bias would just vanish from data because of ML magic, somehow. I didn't get their arguments
I will most remember being an L8 #Technologist getting yelled at by an L8 #AppliedScientist for trying to build what they'd need in the next year instead of making myself a glorified #codemonkey to the #AppliedScientist clique. In the end, they needed exactly what we built.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
