Jeong-Kyu Han

Neuroscientist (Biology + Technology + Philosophy); Learning & Memory, Consciousness

[Bodhi @BodhiCogSci]

Here John Krakauer (Hopkins) discussing why he thinks the current 4E is just a wrong step! Gem!

[Trends in Cognitive Sciences @TrendsCognSci]

Attention in the wild: balancing flexibility and stability

Review by Maëlle Lerebourg (@MaelleLerebourg), Surya Gayet, Floris P. de Lange, & Marius V. Peelen (@MariusPeelen)

Free access before June 23: https://t.co/XOWF0fabW8

[CLaE @leafs_s]

Layers of Mind: Affect as Field History, Prediction as Field Organization — Returning to the Deferred Question of Qualia in the Natural Criticality Hypothesis

https://t.co/lcPdIYCeOu

[Luiz Pessoa @PessoaBrain]

𝗖𝗼𝗴𝗻𝗶𝘁𝗶𝗼𝗻 𝗲𝗺𝗲𝗿𝗴𝗲𝘀 𝗳𝗿𝗼𝗺 𝗽𝗵𝗮𝘀𝗲 𝗱𝘆𝗻𝗮𝗺𝗶𝗰𝘀 𝗼𝗳 𝗶𝗻𝘁𝗿𝗶𝗻𝘀𝗶𝗰 𝗰𝗼𝗼𝗿𝗱𝗶𝗻𝗮𝘁𝗶𝗼𝗻
Timing is everything! The brain dynamics theme develops further...
https://t.co/PU6w1fFRn0

[Neuron @NeuroCellPress]

Online now: Linking neural manifolds to circuit structure in recurrent networks https://t.co/jQFWF686aR

[Dhairya @dkare1009]

BREAKING: MIT just mass released their Al library for free. (Links included)

I went through these and honestly... this is better than most paid courses I've seen.

Here's the full list of books:

Foundations

1. Foundations of Machine Learning Core algorithms explained. Theory meets practice.

2. Understanding Deep Learning Neural networks demystified. Visual explanations included.

3. Machine Learning Systems Production-ready architecture. System design principles.

Advanced Techniques

4. Algorithms for ML Computational thinking simplified. Decision-making frameworks.

5. Deep Learning The definitive textbook. Covers everything deeply.

Reinforcement Learning

6. RL Basics (Sutton & Barto) The classic. Agent training fundamentals.

7. Distributional RL Beyond expected rewards. Advanced theory.

8. Multi-Agent Systems Agents working together. Coordination and competition.

9. Long Game Al Strategic agent design. Future-focused thinking.

Ethics & Probability

10. Fairness in ML Bias detection. Responsible Al practices.

11. Probabilistic ML (Part 1 & 2)

Links: https://t.co/AhDqm9x1QC

Most people pay thousands for bootcamps that teach half of this.

Bookmark it. Start anywhere. Just start.

Repost for others Follow for more insights on Al Agents.

MIT's books on Al

Foundations

1. Foundations of Machine Learning - https://t.co/HxbXfsDIl6

2. Understanding Deep Learning - https://t.co/AyeQav2yzN

3. Machine Learning Systems - https://t.co/0AxGtjBFwA

Advanced Techniques

4. Algorithms for ML - https://t.co/LOjFeK1hut

5. Deep Learning - https://t.co/Ztmu7X6gNM

Reinforcement Learning

6. RL Basics (Sutton & Barto) - https://t.co/HAWxL28df1

7. Distributional RL - https://t.co/VB1zBuSzag

8. Multi-Agent Systems - https://t.co/3tWqJaimYn

9. Long Game Al - https://t.co/vYDuy1XKT2

Ethics & Probability

10. Fairness in ML - https://t.co/B4lAj2ivpF

11. Probabilistic ML (Part 1) - https://t.co/folJrX24sf

12. Probabilistic ML (Part 2) - https://t.co/BMOjc8qSqZ

[CLaE @leafs_s]

Trends in Neurosciences

The feasibility of artificial consciousness through the lens of neuroscience

https://t.co/VdqYp06MkB

[allen institute @AllenInstitute]

🧠📢 New preprint alert

Large-scale ephys is exploding but spike sorting remains the computational bottleneck. A 2-hr, 6-probe Neuropixels 2.0 Quad Base session can take over a week to sort on a single machine. Here's a better solution. 🧵

[Decision Neuroscience and Neuroeconomics Papers @decisionneurop]

Neural variability in the medial prefrontal cortex contributes to efficient adaptive behavior https://t.co/TRuUvasXjg

[CogSci Society @cogsci_soc]

📣 Calling early-career cognitive scientists in the Asia-Pacific!

The CogSci Asia-Pacific Meetup Kickoff is coming:

📍 Dec 6–7, 2025 | Tokyo
🌱 Retreat-style event, community building, and cross-cultural exchange.

Details: https://t.co/vbxkzx2oPI
#CogSci2025 #CognitiveScience

[Math Cafe @Riazi_Cafe_en]

Cambridge's "Mathematics of Machine Learning" by Rajen D. Shah

Notes (PDF): https://t.co/aJLHyQ2lMm

Examples: https://t.co/oBH6HJwjDK

[Big Think @bigthink]

What if our intuition about consciousness is wrong? @annakaharris

"We have no direct evidence that consciousness arises from complexity. We assume it because it seems that way to us, based on what we now understand to be illusions created by the brain."

[Jeong-Kyu Han @jayhan97]

A: Do you know why consciousness research seems so far off?
B: Because it’s hard?
A: If the problem of consciousness gets solved, they’ll be out of a job.
B: …

The chapter on consciousness is usually tucked away at the very end of neuroscience textbooks.

[Jürgen Schmidhuber @SchmidhuberAI]

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.

[Trends in Cognitive Sciences @TrendsCognSci]

What will society think about AI consciousness? Lessons from the animal case

Science & Society by Lucius Caviola, Jeff Sebo, & Jonathan Birch, https://t.co/UM7R8v06nb

[Jeong-Kyu Han @jayhan97]

Crazy stuff!!
We're "Dancing Qualia" David Chalmers behind us.

[Jeong-Kyu Han @jayhan97]

Literally "Hot" Discussion Section ASSC25

[CLaE @leafs_s]

:Trends in Cognitive Sciences

The interoceptive origin of reinforcement learning
https://t.co/PmrBiSQ4um

[Trends in Cognitive Sciences @TrendsCognSci]

Predictive coding in the human olfactory system

Opinion by Sam Lyons & Jay Gottfried
https://t.co/Aa4JwNcqn7

[CLaE @leafs_s]

Nature Neuroscience

Spatial reasoning via recurrent neural dynamics in mouse retrosplenial cortex

https://t.co/IAgbZNlvgx