DeepLearningThesis
@deep_thesis
Followers
43
Following
19
Media
7
Statuses
59
One metric to ruler them all. https://t.co/EBdHZSFF6S
Gothenburg, Sweden
Joined January 2018
The guys at @Stanford and @Princeton should really check the performance of the #ImageNet website, incredibly slow response time. #DeepLearning #ComputerVision
0
0
1
How does one know that one's model has converged? And to which minima? Which effects does this have? Is it possible to compare minima between models? #DeepLearning #deepthoughts.
0
0
0
great blog post by @parasdahal explaining clearly how Softmax and Cross Entropy Loss actually works
0
1
3
Great pod by @twimlai with @goodfellow_ian and Sandy Huang - you guys are so pedagogic and professional, we need more people like you! Recognised the dog as fish example from the Influence Functions paper btw, great paper!
Today we're joined by @goodfellow_ian of @GoogleBrain @googleresearch and Sandy Huang, PhD Student at @UCBerkeley, to discuss their paper "Adversarial Attacks on Neural Network Policies." Follow the link to check it out!
0
1
8
Us debugging legacy influence function code. Hard at work or hardly working? #InfluenceFunctions #TensorFlow #DeepLearning
0
0
0
RT @MFordFuture: Flying taxi drones from @kittyhawkcorp are now being tested in New Zealand.#RiseoftheRobots.@andrewrsorkin .
0
10
0
great blog post by @EliotAndres introducing some very useful @ProjectJupyter extensions!
🤓 New blog post: My 5 favorite Jupyter Notebook Extensions: With pieces of advice (tweets) from @radekosmulski and @randal_olson.
0
0
1
Favorite recent jupyter notebook discovery - the %debug magic:. 1. Get an exception. 2. Insert a new cell, type %debug and run it. An interactive debugger will open bringing you to where the exception occurred and allowing you to look around!
0
0
0
Great pod by @twimlai talking to Ksenia Konyushkova about her work in #ActiveLearning etc. Wonder if similar approach could be taken to similarity in trained models, or if influence functions could be applied to active learning #LearningActiveLearning #DeepLearning
Live!! Today we're joined by Ksenia Konyushkova, PhD Student in the CVLab at @EPFL_en, with whom we discuss her interesting research into ways we might apply machine learning to ease the challenge of creating labeled datasets for machine learning.
0
3
8
Yesterday we took part in #hashcode at the #NewMinds hub in #gothenburg! We didn't win, but managed to submit a solution, which made us happy enough! #HappyHacking! #DataScience #hashcode18
0
0
0
Interesting thread about what #AI actually can do
AI learning performance is not yet even in the same continent as biological learning. Good to see people exploring the deep science of learning still. Readable summary: and source material:
0
0
1
Nice inspiration from @IBMWatson @xprize regarding #AI for global good. Their approach is much "track everything that can be tracked, make everything IoT". Wonder how to make it more concrete.
0
0
1
RT @frick: Bakom scenen men framför kameran idag hos @EFNTV - Daniel @Langkilde från @Annotell för ett snack om bl.a. #artificiellintellige….
0
3
0
Do you also find it hard to grasp all different #ComputerVision buzzwords? Have look at our blog post where we give a brief summary of the most common areas! #DeepLearning #AI
0
0
0
Interesting post! Have a look at our blog post if you want to understand the math in #ConvNet better.
0
0
1
Do you also understand the intuition about CNNs, but have a hard time understanding how it actually works mathematically? Check out our blog post where we try to clarify this! #CNN #mathematics #DeepLearning #AI.
0
1
0