Jürgen Schmidhuber engagement report

Best tweets

• Jun 4, 20263.6x their median

  We just launched Canada’s new AI Strategy: AI For All.    We’re taking control of our future — with AI that’s governed by Canadian values, AI that’s accountable to Canadians, and AI that serves all Canadians.

  3.4K3813.1K9951.3M viewsView on X
• Sep 12, 20263.4x their median

  Prediction: Google just cracked Recursive Self Improvement and the rest of the labs are trying to slow them down by pitching doom and gloom to regulators.

  6.9K30116763501K viewsView on X
• Nov 28, 20252.2x their median

  Yann LeCun’s 1989 convolutional neural network demo, the foundation for the CNNs we still use today. It's amazing how far we've come since then! https://t.co/rblFlu2CHa

  4.3K4469840751K viewsView on X
• Aug 3, 2025

  Who invented convolutional neural networks (CNNs)? 1969: Fukushima had CNN-relevant ReLUs [2]. 1979: Fukushima had the basic CNN architecture with convolution layers and downsampling layers [1]. Compute was 100 x more costly than in 1989, and a billion x more costly than today. 1987: Waibel applied Linnainmaa's 1970 backpropagation [3] to weight-sharing TDNNs with 1-dimensional convolutions [4]. 1988: Wei Zhang et al. applied "modern" backprop-trained 2-dimensional CNNs to character recognition [5]. All of the above was published in Japan 1979-1988. 1989: LeCun et al. applied CNNs again to character recognition (zip codes) [6,10]. 1990-93: Fukushima’s downsampling based on spatial averaging [1] was replaced by max-pooling for 1-D TDNNs (Yamaguchi et al.) [7] and 2-D CNNs (Weng et al.) [8]. 2011: Much later, my team with Dan Ciresan made max-pooling CNNs really fast on NVIDIA GPUs. In 2011, DanNet achieved the first superhuman pattern recognition result [9]. For a while, it enjoyed a monopoly: from May 2011 to Sept 2012, DanNet won every image recognition challenge it entered, 4 of them in a row. Admittedly, however, this was mostly about engineering & scaling up the basic insights from the previous millennium, profiting from much faster hardware. Some "AI experts" claim that "making CNNs work" (e.g., [5,6,9]) was as important as inventing them. But "making them work" largely depended on whether your lab was rich enough to buy the latest computers required to scale up the original work. It's the same as today. Basic research vs engineering/development - the R vs the D in R&D. REFERENCES [1] 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. [2] 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 (ReLUs), now used in many CNNs. [3] S. Linnainmaa (1970). Master's Thesis, Univ. Helsinki, 1970. The first publication on "modern" backpropagation, also known as the reverse mode of automatic differentiation. (See Schmidhuber's well-known backpropagation overview: "Who Invented Backpropagation?") [4] A. Waibel. Phoneme Recognition Using Time-Delay Neural Networks. Meeting of IEICE, Tokyo, Japan, 1987. Backpropagation for a weight-sharing TDNN with 1-dimensional convolutions. [5] 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 backpropagation-trained 2-dimensional CNN, with applications to English character recognition. [6] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel: Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, 1(4):541-551, 1989. See also Sec. 3 of [10]. [7] K. Yamaguchi, K. Sakamoto, A. Kenji, T. Akabane, Y. Fujimoto. A Neural Network for Speaker-Independent Isolated Word Recognition. First International Conference on Spoken Language Processing (ICSLP 90), Kobe, Japan, Nov 1990. A 1-dimensional convolutional TDNN using Max-Pooling instead of Fukushima's Spatial Averaging [1]. [8] Weng, J., Ahuja, N., and Huang, T. S. (1993). Learning recognition and segmentation of 3-D objects from 2-D images. Proc. 4th Intl. Conf. Computer Vision, Berlin, pp. 121-128. A 2-dimensional CNN whose downsampling layers use Max-Pooling (which has become very popular) instead of Fukushima's Spatial Averaging [1]. [9] In 2011, the fast and deep GPU-based CNN called DanNet (7+ layers) achieved the first superhuman performance in a computer vision contest. See overview: "2011: DanNet triggers deep CNN revolution." [10] How 3 Turing awardees republished key methods and ideas whose creators they failed to credit. Technical Report IDSIA-23-23, Swiss AI Lab IDSIA, 14 Dec 2023. See also the YouTube video for the Bower Award Ceremony 2021: J. Schmidhuber lauds Kunihiko Fukushima.

  2.4K4098965648K viewsView on X
• Mar 31, 2026

  Dr. LeCun's heavily promoted Joint Embedding Predictive Architecture (JEPA, 2022) [5] is the heart of his new company. However, the core ideas are not original to LeCun. Instead, JEPA is essentially identical to our 1992 Predictability Maximization system (PMAX) [1][14]. Details in reference [19] which contains many additional references. Motivation of PMAX [1][14]. Since details of inputs are often unpredictable from related inputs, two non-generative artificial neural networks interact as follows: one net tries to create a non-trivial, informative, latent representation of its own input that is predictable from the latent representation of the other net’s input. PMAX [1][14] is actually a whole family of methods. Consider the simplest instance in Sec. 2.2 of [1]: an auto encoder net sees an input and represents it in its hidden units (its latent space). The other net sees a different but related input and learns to predict (from its own latent space) the auto encoder's latent representation, which in turn tries to become more predictable, without giving up too much information about its own input, to prevent what's now called “collapse." See illustration 5.2 in Sec. 5.5 of [14] on the "extraction of predictable concepts." The 1992 PMAX paper [1] discusses not only auto encoders but also other techniques for encoding data. The experiments were conducted by my student Daniel Prelinger. The non-generative PMAX outperformed the generative IMAX [2] on a stereo vision task. The 2020 BYOL [10] is also closely related to PMAX. In 2026, @misovalko, leader of the BYOL team, praised PMAX, and listed numerous similarities to much later work [19]. Note that the self-created “predictable classifications” in the title of [1] (and the so-called “outputs” of the entire system [1]) are typically INTERNAL "distributed representations” (like in the title of Sec. 4.2 of [1]). The 1992 PMAX paper [1] considers both symmetric and asymmetric nets. In the symmetric case, both nets are constrained to emit "equal (and therefore mutually predictable)" representations [1]. Sec. 4.2 on “finding predictable distributed representations” has an experiment with 2 weight-sharing auto encoders which learn to represent in their latent space what their inputs have in common (see the cover image of this post). Of course, back then compute was was a million times more expensive, but the fundamental insights of "JEPA" were present, and LeCun has simply repackaged old ideas without citing them [5,6,19]. This is hardly the first time LeCun (or others writing about him) have exaggerated LeCun's own significance by downplaying earlier work. He did NOT "co-invent deep learning" (as some know-nothing "AI influencers" have claimed) [11,13], and he did NOT invent convolutional neural nets (CNNs) [12,6,13], NOR was he even the first to combine CNNs with backpropagation [12,13]. While he got awards for the inventions of other researchers whom he did not cite [6], he did not invent ANY of the key algorithms that underpin modern AI [5,6,19]. LeCun's recent pitch: 1. LLMs such as ChatGPT are insufficient for AGI (which has been obvious to experts in AI & decision making, and is something he once derided @GaryMarcus for pointing out [17]). 2. Neural AIs need what I baptized a neural "world model" in 1990 [8][15] (earlier, less general neural nets of this kind, such as those by Paul Werbos (1987) and others [8], weren't called "world models," although the basic concept itself is ancient [8]). 3. The world model should learn to predict (in non-generative "JEPA" fashion [5]) higher-level predictable abstractions instead of raw pixels: that's the essence of our 1992 PMAX [1][14]. Astonishingly, PMAX or "JEPA" seems to be the unique selling proposition of LeCun's 2026 company on world model-based AI in the physical world, which is apparently based on what we published over 3 decades ago [1,5,6,7,8,13,14], and modeled after our 2014 company on world model-based AGI in the physical world [8]. In short, little if anything in JEPA is new [19]. But then the fact that LeCun would repackage old ideas and present them as his own clearly isn't new either [5,6,18,19]. FOOTNOTES 1. Note that PMAX is NOT the 1991 adversarial Predictability MINimization (PMIN) [3,4]. However, PMAX may use PMIN as a submodule to create informative latent representations [1](Sec. 2.4), and to prevent what's now called “collapse." See the illustration on page 9 of [1]. 2. Note that the 1991 PMIN [3] also predicts parts of latent space from other parts. However, PMIN's goal is to REMOVE mutual predictability, to obtain maximally disentangled latent representations called factorial codes. PMIN by itself may use the auto encoder principle in addition to its latent space predictor [3]. 3. Neither PMAX nor PMIN was my first non-generative method for predicting latent space, which was published in 1991 in the context of neural net distillation [9]. See also [5-8]. 4. While the cognoscenti agree that LLMs are insufficient for AGI, JEPA is so, too. We should know: we have had it for over 3 decades under the name PMAX! Additional techniques are required to achieve AGI, e.g., meta learning, artificial curiosity and creativity, efficient planning with world models, and others [16]. REFERENCES (easy to find on the web): [1] J. Schmidhuber (JS) & D. Prelinger (1993). Discovering predictable classifications. Neural Computation, 5(4):625-635. Based on TR CU-CS-626-92 (1992): https://t.co/wJFbdPhwdi [2] S. Becker, G. E. Hinton (1989). Spatial coherence as an internal teacher for a neural network. TR CRG-TR-89-7, Dept. of CS, U. Toronto. [3] JS (1992). Learning factorial codes by predictability minimization. Neural Computation, 4(6):863-879. Based on TR CU-CS-565-91, 1991. [4] JS, M. Eldracher, B. Foltin (1996). Semilinear predictability minimization produces well-known feature detectors. Neural Computation, 8(4):773-786. [5] JS (2022-23). LeCun's 2022 paper on autonomous machine intelligence rehashes but does not cite essential work of 1990-2015. [6] JS (2023-25). How 3 Turing awardees republished key methods and ideas whose creators they failed to credit. Technical Report IDSIA-23-23. [7] JS (2026). Simple but powerful ways of using world models and their latent space. Opening keynote for the World Modeling Workshop, 4-6 Feb, 2026, Mila - Quebec AI Institute. [8] JS (2026). The Neural World Model Boom. Technical Note IDSIA-2-26. [9] JS (1991). Neural sequence chunkers. TR FKI-148-91, TUM, April 1991. (See also Technical Note IDSIA-12-25: who invented knowledge distillation with artificial neural networks?) [10] J. Grill et al (2020). Bootstrap your own latent: A "new" approach to self-supervised Learning. arXiv:2006.07733 [11] JS (2025). Who invented deep learning? Technical Note IDSIA-16-25. [12] JS (2025). Who invented convolutional neural networks? Technical Note IDSIA-17-25. [13] JS (2022-25). Annotated History of Modern AI and Deep Learning. Technical Report IDSIA-22-22, arXiv:2212.11279 [14] JS (1993). Network architectures, objective functions, and chain rule. Habilitation Thesis, TUM. See Sec. 5.5 on "Vorhersagbarkeitsmaximierung" (Predictability Maximization). [15] JS (1990). Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments. Technical Report FKI-126-90, TUM. [16] JS (1990-2026). AI Blog. [17] @GaryMarcus. Open letter responding to @ylecun. A memo for future intellectual historians. Substack, June 2024. [18] G. Marcus. The False Glorification of @ylecun. Don’t believe everything you read. Substack, Nov 2025. [19] J. Schmidhuber. Who invented JEPA? Technical Note IDSIA-3-22, IDSIA, Switzerland, March 2026. https://t.co/fDauPE6T2N

  1.9K1939286730K viewsView on X
• Sep 8, 2026

  there’s only one rightful author who can claim to have solved NS https://t.co/6zYZfdSzWv

  2.0K992420227K viewsView on X
• Jan 29, 2025

  It has been said that AI is the new oil, the new electricity, and the new internet. And the once nimble and highly profitable software companies (MSFT, GOOG, ...) became like utilities, investing in nuclear energy, among other things, to run AI data centres. Open Source and the #DeepSeek #Sputnik have once again shown that such companies "have no moat" in the field of AI. In many talks over the last decade, I mentioned the rich guy I knew when I was young. He had a Porsche with something incredible: a mobile phone. He could call other people who had such a Porsche via a satellite. But 40 years later, everyone had a cheap smartphone in their pocket, which is far superior to what he had in his Porsche. And it's the same with AI. Every five years, compute becomes ten times cheaper - a trend that has continued since the first general-purpose computer was completed in 1941. The basic techniques of modern AI were developed in the last millennium, when compute was still very expensive, but this trend has made them so cheap that AI has been on your smartphone since the 2010s. The trend will not break in the coming decades (the physical Bremermann limit is still a long way off). An AI data centre that is worth 100 billion today will only be worth 1 billion in ten years' time. Soon, small, cheap computers with increasingly efficient open source AI software will do what the large data centres do today. So AI will not be controlled by a few big AI utilities. No, everyone will own cheap but powerful and transparent AI that improves their lives in many ways. See the old motto of @nnaisense founded in 2014: ‘AI∀’ or ‘AI For All’.

  1.6K33612266315K viewsView on X
• Apr 10, 2026

  Neural Computers https://t.co/XVk9bCLGbm https://t.co/ov0qdU1BSb

  1.7K2584446303K viewsView on X
• Dec 23, 2022

  Machine learning is the science of credit assignment. My new survey (also under arXiv:2212.11279) credits the pioneers of deep learning and modern AI (supplementing my award-winning 2015 deep learning survey): https://t.co/MfmqhEh8MA P.S. Happy Holidays! https://t.co/or6oxAOXgS

  1.5K3263934507K viewsView on X
• Mar 10, 2026

  Everybody is talking about recursive self-improvement (RSI) and meta learning. Here is my old 2020 talk about this [1]. It has aged well. Example: humans still define the starts & ends of trials of many modern meta learners. My RSI systems since 1994 LEARN to (re)define them [2]! [1] Meta Learning Machines in a Single Lifelong Trial (talk for workshops at ICML 2020 and NeurIPS 2021, based on earlier talks since 1994). Abstract: the most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main driver of my research since I wrote a thesis on it in 1987 [2]. Here I summarize our work on meta reinforcement learning with self-modifying policies in a single lifelong trial (since 1994), and mathematically optimal meta-learning through the self-referential Gödel Machine (since 2003). Many additional publications on meta-learning since 1987 can be found in the RSI overview [2]. [2] J. Schmidhuber (AI Blog, 2020-2025). 1/3 century anniversary of first publication on recursive self-improvement (RSI) and meta learning machines that learn to learn (1987). For its cover I drew a robot that bootstraps itself. 1992-: gradient descent-based neural meta learning. 1994-: meta reinforcement learning with self-modifying policies. 1997: meta RL plus artificial curiosity and intrinsic motivation. 2002-: asymptotically optimal meta learning for curriculum learning. 2003-: mathematically optimal Gödel Machine. 2020-: new stuff!

  1.4K1784822281K viewsView on X

Ranked by total interactions across everything we have tracked for this account, which is a longer history than the 30-day window the rates above use. The multiple compares each post to this account's own median.

Keep going