正在加载视频...
视频加载失败
In 1993, the world's first handwritten digit recognition convolutional neural network achieved a major Al milestone
11 条评论
This is Yann LeCun's ' LeNet-5' Yann LeCun, along with his colleagues, made significant contributions to the field of neural networks in 1998. They proposed the LeNet-5, a convolutional neural network that was one of the earliest and most influential in the field, especially for image recognition tasks like handwritten digit recognition. This network was a pioneering work in deep learning and helped to advance the development of more complex neural network architectures. LeNet-5 was particularly notable for its ability to recognize handwritten characters, which was a practical application demonstrated by LeCun and his team. They showed that their model could read millions of checks per day, which was a significant achievement for neural networks at the time. The work of Yann LeCun and his team in the late 1990s laid the groundwork for many of the advancements in deep learning and neural networks that we see today.
The first community-owned crypto media outlet has partnered with DAIC, a leading Web3 infrastructure & non-custodial staking provider, to pioneer a new community validator model. Stake with us.
Split flat display test, it'll be 10 digits display
It may not seem significant now, especially in the eyes of young children. But back then, it was a pioneering system worthy of admiration.
Turns out we just needed to scale this up and it would reliably find cats.
Welcome to the comments section where first 30 comments won't relate to the post
Boston Dynamic just unveiled their newest Atlas robot. This is not a render.
In 2018, the first AI scripted commercial debuted. It was for Lexus
That was my birth year
El el için ağlamaz, başına kara bağlamaz.
impressive
![Fukushima's video (1986) shows a CNN that recognises handwritten digits [3], three years before LeCun's video (1989). CNN timeline taken from [5]: ★ 1969: Kunihiko Fukushima published rectified linear units or ReLUs [1] which are now extensively used in CNNs. ★ 1979: Fukushima published the basic CNN architecture with convolution layers and downsampling layers [2]. He called it neocognitron. It was trained by unsupervised learning rules. Compute was 100 times more expensive than in 1989, and a billion times more expensive than today. ★ 1986: Fukushima's video on recognising hand-written digits [3]. ★ 1988: Wei Zhang et al had the first "modern" 2-dimensional CNN trained by backpropagation, and also applied it to character recognition [4]. Compute was about 10 million times more expensive than today. ★ 1989-: later work by others [5]. REFERENCES (more in [5]) [1] K. Fukushima (1969). Visual feature extraction by a multilayered network of analog threshold elements. IEEE Transactions on Systems Science and Cybernetics. 5 (4): 322-333. This work introduced rectified linear units or ReLUs, now widely used in CNNs and other neural nets. [2] K. Fukushima (1979). Neural network model for a mechanism of pattern recognition unaffected by shift in position—Neocognitron. Trans. IECE, vol. J62-A, no. 10, pp. 658-665, 1979. The first deep convolutional neural network architecture, with alternating convolutional layers and downsampling layers. In Japanese. English version: 1980. [3] Movie produced by K. Fukushima, S. Miyake and T. Ito (NHK Science and Technical Research Laboratories), in 1986. YouTube: [4] W. Zhang, J. Tanida, K. Itoh, Y. Ichioka. Shift-invariant pattern recognition neural network and its optical architecture. Proc. Annual Conference of the Japan Society of Applied Physics, 1988. First "modern" backpropagation-trained 2-dimensional CNN, applied to character recognition. [5] J. Schmidhuber (AI Blog, 2025). Who invented convolutional neural networks?](https://image.24vids.com/tw-1995875626092315116/amplify_video_thumb/1995874290957246464/img/eSqWV92Ig7PvvIiH.jpg)
