The Research paper that changed the world...
Anything happening in AI today can be traced back to this one brief moment in history... Share your favourite papers. GPT ftw :)
https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Dihaadi
Stealth
4 months ago
TheOatmeal
Stealth
4 months ago
Dihaadi
Stealth
4 months ago
WhiteLotus23
Stealth
4 months ago
Discover More
Curated from across
Data Scientists on
by Gooner7
Goldman Sachs
This Paper will make you smarter than 90% AI Engineers
I am giving a deep overview of why this is extremely important. This paper is by the three greatest researchers in the field of AI ever. They are considered to be the godfathers of AI. This paper essentially brought deep learning into the zeitgeist of the last decade. We saw the advent of some of the greatest advancement in AI. The advancements in AI are similar to the Industrial revolution, where you could not even guess the change in the nature of jobs, society, life and the world over the next 5 years. The world is changing, so don't become a horse carriage driver now, be a steam engine engineer. Compete or get outcompeted.
Yann Lecun, Yoshua Bengio, Geoffrey Hinton
https://hal.science/hal-04206682/document
Data Scientists on
by Gooner7
Goldman Sachs
This Research Paper changed my life forever.
It was one of the papers that was discussed in my interview at Goldman. I came to know about this research paper a few years back after consulting a friend doing an ML PhD at University of Maryland, College Park. The explanation of the paper: 1. Initialize the neural network with small random values typically (-0.1,0.1) to avoid symmetry issues. 2. Now get ready to do Forward propagation: you pass thetraining data through the multilayer perceptron and compute the output. For each neuron in the MLP, calculate the weighted sum of its inputs and apply the activation function. (my favourite is tanh for LSTM applications) 3. Now compute the loss using a loss function like mean squared error, between output computed and the actual value. 4. Now get ready to do backpropagation, where you need to calculate the gradient of the loss function with respect to each weight by propagating the error backward through the network. 5. So, compute partial derivatives of the loss with respect to each weight, starting from the output layer and moving back to the input layer. 6. Here is the fun part: update the weights using the gradients obtained from the backward pass. here people usually use adam optimizer, which allows for accelerated stochastic gradient descent. Fun trivia: Adam stands for "Adaptive Moment Estimation". 7. Now repeat the forward and backward propagation process for numerous tries until theperformance of the model stabilizes.
https://www.iro.umontreal.ca/~vincentp/ift3395/lectures/backprop_old.pdf
Data Scientists on
by Gooner7
Goldman Sachs
OpenAI Cofounder: "Learn these 30 research papers and you will know 90% of what matters today."
Please like and bookmark this if you find it useful. I have acess to the top AI researchers and ML PhDs working on the cutting edge in India and the US, will post some good content if this crosses 100 likes. Ilya Sutskever, OpenAI cofounder, gave John Carmack this reading list of approximately 30 research papers and said, ‘If you really learn all of these, you’ll know 90% of what matters today.’ FYI: John Carmack is also considered to be the greatest programmer of all time.
https://arc.net/folder/D0472A20-9C20-4D3F-B145-D2865C0A9FEE
Data Scientists on
by Gooner7
Goldman Sachs
The Gods of AI made "Generative Adversarial Networks"
Please give this post +1 like, I am getting demoralized when I see bad posts get 100s of likes but a good post like this gets no likes whatsoever. If I don't get more than 100 likes then I will stop posting research papers here. Ian Goodfellow and his collaborators published a groundbreaking paper that revolutionized the field of artificial intelligence, especially in generative modeling. This is the first time the world was introduced to Generative Adversarial Networks (GANs), a revolutionary framework that pits two neural networks against each other in a game-theoretic scenario. Unlike traditional generative models, GANs consist of a generator and a discriminator. The generator creates data samples, while the discriminator evaluates them, distinguishing between real and generated data. This novel approach not only significantly enhanced the quality and realism of generated data but also provided a robust framework for training generative models in an unsupervised manner. Ian Goodfellow, along with his colleagues, not only pushed the boundaries of generative modeling but also set the stage for a plethora of applications across various domains, from image synthesis and enhancement to data augmentation and beyond. Their innovative work demonstrated the potential of adversarial training in neural networks, opening new avenues in both theoretical research and practical applications in AI.
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a gener...
https://arxiv.org/pdf/1406.2661
