History interview questions
The people, papers and moments that built the field, from the perceptron to the Transformer.
35 questions in this category.
The cards run from least squares and Bayes through the perceptron, backpropagation and MNIST to AlexNet, AlphaGo and the Transformer: the papers, datasets and people whose names turn up in interview small talk, and in the citations behind everything else in the deck.
Start with these
- Who invented the perceptron?
- When was the Turing Test created?
- Who envisioned and created the ImageNet dataset?
- Which computer scientists received the Turing Award for their contributions to deep learning?
- What is the name of the computer program that first beat a professional Go player without a handicap?
- Who is known as the creator of the GAN architecture?
- Ian Goodfellow.
- The least squares method was first published by which famous French mathematician?
- Adrien-Marie Legendre.
- In 1812 Laplace published "Théorie analytique des probabilités", in which he stated a famous theorem. Which theorem was it?
- Bayes' theorem, which Laplace had found independently in 1774 and set out here as a general principle for inferring causes from observed events. The same book is also known for Laplace's central limit theorem.
- Andrey Markov first described the techniques he used to analyse a poem, and these techniques later became known as Markov chains. True or false?
- False as stated. Markov introduced the chains in a 1906 paper on the law of large numbers for dependent variables. His 1913 study of vowel and consonant sequences in the first 20,000 letters of Pushkin's Eugene Onegin was their first application to real data, not their origin.
- Who invented the perceptron?
- Frank Rosenblatt. Bonus. The invention of the perceptron generated a great deal of excitement and was widely covered in the media.
- In 1970 Seppo Linnainmaa described reverse-mode automatic differentiation in his master's thesis. This corresponds to the modern version of:
- Backpropagation — reverse-mode automatic differentiation, which gets the gradient of a scalar loss with respect to every parameter in roughly one backward pass. Rumelhart, Hinton and Williams rediscovered and popularised it for neural networks in 1986.
- In 1995 Corinna Cortes and Vladimir Vapnik published their work on a supervised learning algorithm called:
- Support Vector Machines
- What was the name of the first computer to beat a reigning world chess champion?
- Deep Blue, built by IBM. It won a game against Garry Kasparov in 1996 but lost that match, then won the 1997 rematch 3½-2½.
- Who invented the LSTM architecture in deep learning?
- Sepp Hochreiter and Jürgen Schmidhuber in 1997.
- When was Torch released?
- 2002, when Ronan Collobert, Samy Bengio and Johnny Mariéthoz at IDIAP described the C++ library. The better-known Lua-based Torch7 followed in 2011.
- Who envisioned and created the ImageNet dataset?
- Fei-Fei Li, who argued from 2007 that models were starved of data rather than ideas and used crowdsourced labelling to reach roughly 14 million images across 20,000+ categories. The 2012 ILSVRC contest run on it is where AlexNet made deep learning mainstream.
- What is the name of the computer program that first beat a professional Go player without a handicap?
- AlphaGo, by Google DeepMind. It beat European champion Fan Hui 5-0 in October 2015, the first win by a computer over a professional on a full 19 × 19 board without handicap.
- Which computer scientists received the Turing Award for their contributions to deep learning?
- Yoshua Bengio, Geoffrey Hinton, and Yann LeCun.
- When was the nearest neighbor algorithm created?
- 1951: Evelyn Fix and Joseph Hodges introduced nearest neighbor classification in a US Air Force report. The often-quoted 1967 is Thomas Cover and Peter Hart's paper proving that 1-NN's error is at most twice the Bayes error.
- When was the Turing Test created?
- 1950, in Turing's paper "Computing Machinery and Intelligence", which swapped the question of whether machines think for an imitation game judged over text. Its weakness is that it rewards convincing conversation rather than understanding — a critique now aimed straight at LLMs.
- Who coined the term deep learning in 2006?
- Geoffrey Hinton is usually credited: his 2006 deep belief net paper with Osindero and Teh made the term popular. Strictly, he didn't coin it. Rina Dechter used "deep learning" in 1986, and Igor Aizenberg and colleagues applied it to neural networks in 2000.
- Who is the creator of Keras?
- François Chollet.
- Who are credited with the creation of R?
- Ross Ihaka and Robert Gentleman.
- Who is known as the founding father of convolutional nets?
- Yann LeCun, who at AT&T Bell Labs in 1989 first trained convolutional networks end to end with backpropagation (later LeNet). The architecture builds on Kunihiko Fukushima's 1980 neocognitron.
- Who are known as the "Godfathers of AI"?
- Geoffrey Hinton, Yann LeCun, and Yoshua Bengio.
- Was Bayes's Theorem published after his death?
- Yes. Bayes died in 1761, and his friend Richard Price edited his essay and presented it to the Royal Society in December 1763, two years later. Pierre-Simon Laplace, working independently, stated the same principle in 1774 and developed it further over the following decades, notably in his Théorie analytique des probabilités (1812).
- What object did Yann LeCun use in his NIPS 2016 keynote to describe the 'layers' of intelligence?
- Cake
- What language was the original AlexNet (ILSVRC 2012) written in?
- CUDA and C++, in Alex Krizhevsky's cuda-convnet code, with Python scripts driving training.
- What was the final score of the 2016 match between Google DeepMind’s AlphaGo and Go grandmaster Lee Sedol?
- 4-1 to AlphaGo: it won games 1, 2, 3 and 5, and Lee Sedol won game 4.
- Whose notable students include Ruslan Salakhutdinov, Ilya Sutskever and Yann LeCun?
- Geoffrey Hinton. Salakhutdinov and Sutskever did their PhDs with him at the University of Toronto; LeCun was his postdoc there from 1987 to 1988.
- What was the output dimension of the embedding layers and sub-layers of the original Transformer (Attention Is All You Need, 2017)?
- 512 (d_model) in the base model. The larger Transformer (big) in the same paper used 1024.
About · Quizzes · History of AI · To suggest new questions or report an error send me a dm.