Эксперт по сдаче вступительных испытаний в ВУЗах
Additional tasks to unit “Neural networks”
Task 1. Read and translate the text. Write 10 special questions to the text.
Historywiss
Warren Mc Culloch and Walter Pitts (1943) created a computational model for neural networks based on mathematics and algorithms. They called this model threshold logic. The model paved the way for neural network research to split into two distinct approaches. One approach focused on biological processes in the brain and the other focused on the application of neural networks to artificial intelligence.
In the late 1940s psychologist Donald Hebb created a hypothesis of learning based on the mechanism of neural plasticity that is now known as Hebbian leaning. Hebbian learning is considered to be a ‘typical’ unsupervised leaning rule and its later variants were early models for long term potention. These ideas started being applied to computational models in 1948 with Turning’s B- type machines.
Farley and Wesley A. Clark (1954) first used computational machines, then called calculators, to simulate a Hebbian network at MIT. Other neural network computational machines were created by Rochester, Holland, Habit, and Duda (1956).
Frank Rosenblatt (1958) created the perception, an algorithm for pattern recognition based on a two-layer learning computer network using simple addition and subtraction. With mathematical notation, Rosenblatt also described circuitry not in the basic perceptron, such as the exclusive-or circuit, a circuit whose mathematical computation could not be processed until after the back propagation algorithm was created by Paul Werbos (1975).
Neural network research stagnated after the publication of machine learning research by Marvin Minsky and Seymour Papert (1969). They discovered two key issues with the computational machines that processed neural networks. The first issue was that single-layer neural networks were incapable of processing the exclusive-or circuit. The second significant issue was that computers were not sophisticated enough to effectively handle the long run time required by large neural networks. Neural network research slowed until computers achieved greater processing power. Also key later advances was the back propagation algorithm which effectively solved the exclusive-or problem (Werbos 1975)
The parallel distributed processing of the mid-1980s became popular under the name connectionism. The text by Davia E. Rumelhaet and James Mc Cleeand (1986) provided a full exposition on the use of connectionism in computers to simulate neural processes. Neural networks, as used in artificial intelligence, have traditionally been viewed as simplified models of neural processing in the brain, even though the relation between this model and brain biological architecture is debated, as it is not clear to what degree artificial neural networks mirror brain function. In the 1990s, neural networks were overtaken in popularity in machine learning by support vector machines and other, much simpler methods such as linear classifiers. Renewed interest in neural nets was sparked in the 2000s by the advent of deep learning.
Task 2. Work in pairs. Answer the questions of your partner. Ask him/her yours.
Task 3. Complete the sentences in an appropriate way.
Successes in pattern recognition contest since 2009
1) to design, 2) handwritten digits problem, 3) recurrent neural networks, 4) multidimensional long short term memory, 5) pattern recognition
Between 2009 and 2012, a) ……………….and deep feed forward neural networks developed in the research group of Jurgen Schmidhuber at the Swiss AI Lab IDSIA have won eight international competitions in b)………. and machine learning. For example, the bi-directional and c) ………… (LSTM) of Alex Graves et al. won three competitions in connected handwriting recognition at the 2009 International Conference on Document Analysis and Recognition (ICDAR), without any prior knowledge about the three different languages to be learned. Fast GPU-based implementations of this approach by Dan Ciresan and colleagues at IDSIA have won several pattern recognition contests, including the IJCNN 2011 Traffic Sign Recognition Competition, the ISBI 2012 Segmentation of Neuronal Structures in Electron Microscopy Stacks challenge, and others. Their neural networks also were the first artificial pattern recognizers to achieve human-competitive or even superhuman performance on important benchmarks such as traffic sign recognition (IJCNN 2012), or the MNIST d)………… of Yann LeCun at NYU. Deep, highly nonlinear neural architectures similar to the 1980 neocognitron by Kunihiko Fukushina and the «standard architecture of vision» can also be pre-trained by unsupervised methods of Geoff Hinton’s lab at University of Toronto. A team from this lab won a 2012 contest sponsored by Merck e) ………. software to help find molecules that might lead to new drugs.
Task 3. Look through the information of the unit “Boolean algebra”. Write a short essay of 150 words using it.
Ссылка на первоисточник:
https://www.mgpu.ru
